Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 36045
    Prev
    Next
    INDEX
    Explanations

    Circuit

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    (mapped
    -0.07
     Amid
    -0.06
     Citizen
    -0.06
    삮
    -0.06
    People
    -0.06
     muchas
    -0.06
    /gl
    -0.06
    在线咨询
    -0.06
     couples
    -0.06
     Gal
    -0.06
    POSITIVE LOGITS
     дорог
    0.08
    指望
    0.08
     bekom
    0.07
     넘
    0.07
     knives
    0.07
     Imported
    0.07
    饮用水
    0.07
    Enumerable
    0.07
     חוק
    0.07
    ERO
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.