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

    Neuronpedia

    APICircuit 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. 6953
    Prev
    Next
    INDEX
    Explanations

    reserved

    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
     המת
    -0.08
     שהם
    -0.07
     experimenting
    -0.07
    כלול
    -0.07
     Filipino
    -0.07
    🤧
    -0.07
    _icon
    -0.06
     sparking
    -0.06
    _ACCOUNT
    -0.06
     שצריך
    -0.06
    POSITIVE LOGITS
     toilet
    0.08
    ocracy
    0.07
    ?↵↵↵↵↵↵
    0.07
    ole
    0.07
     كامل
    0.06
    scape
    0.06
    Tracking
    0.06
    	top
    0.06
     cancellation
    0.06
    淡定
    0.06
    Activations Density 0.000%

    No Known Activations