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

    Neuronpedia

    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. 15-RESID-POST-AA
    11. 11885
    Prev
    Next
    INDEX
    Explanations

    Scientific nomenclature

    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
     moderation
    -0.07
    百万
    -0.07
    多い
    -0.06
    (World
    -0.06
     Heart
    -0.06
    (admin
    -0.06
     hottest
    -0.06
     Majority
    -0.06
    مدار
    -0.06
    /docs
    -0.06
    POSITIVE LOGITS
    _SK
    0.08
    ケ
    0.08
    .active
    0.08
    "My
    0.07
    入园
    0.07
    _scalar
    0.07
    .RequestMapping
    0.07
    .Apply
    0.07
    ʙ
    0.07
    帶
    0.07
    Activations Density 0.110%

    No Known Activations