© 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. 11-RESID-POST-AA
    11. 86898
    Prev
    Next
    INDEX
    Explanations

    FC

    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_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
     fishing
    -0.08
     sle
    -0.07
    Little
    -0.07
    領
    -0.07
     frozen
    -0.07
    (Const
    -0.07
    Either
    -0.07
    (Bytes
    -0.06
    przed
    -0.06
     crit
    -0.06
    POSITIVE LOGITS
    解决方案
    0.07
    AE
    0.07
    为中国
    0.06
    #af
    0.06
    transport
    0.06
     GAP
    0.06
    �
    0.06
     contact
    0.06
    REFERRED
    0.06
    כ
    0.06
    Activations Density 0.001%

    No Known Activations