© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 64624
    Prev
    Next
    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    The neuron detects special conversation boundary and role-marking tokens (e.g., the <|im_start|>, <|im_end|>, and role labels like "user"/"assistant").

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     actividad
    -0.07
    rier
    -0.07
     scope
    -0.07
    聚焦
    -0.07
    ancell
    -0.07
    짱
    -0.07
    iam
    -0.07
    ritical
    -0.07
    �
    -0.07
     Profile
    -0.07
    POSITIVE LOGITS
     Enforcement
    0.07
     oats
    0.07
    وها
    0.07
     asm
    0.07
     Fired
    0.07
     вмест
    0.07
    <|im_end|>
    0.07
     negotiation
    0.07
     cresc
    0.07
     updater
    0.07
    Activations Density 0.379%

    No Known Activations