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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 15-RESID-POST-AA
    11. 115588
    Prev
    Next
    INDEX
    Explanations

    we

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Nh
    -0.08
    Danger
    -0.07
    évén
    -0.07
    <Event
    -0.07
     bind
    -0.07
    Org
    -0.07
    /DTD
    -0.07
    év
    -0.06
    ých
    -0.06
    "This
    -0.06
    POSITIVE LOGITS
     submarine
    0.07
     councill
    0.07
     envision
    0.07
    钿
    0.07
     appreciate
    0.07
    坚
    0.07
    (serializers
    0.06
    arton
    0.06
    उ
    0.06
    _ui
    0.06
    Activations Density 0.008%

    No Known Activations