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. 87909
    Prev
    Next
    INDEX
    Explanations

    technical specifications

    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
     shri
    -0.07
    温馨提示
    -0.07
    /self
    -0.07
     coerce
    -0.07
    orry
    -0.07
     usuarios
    -0.07
     reinforced
    -0.07
    xz
    -0.07
    nst
    -0.07
     notified
    -0.07
    POSITIVE LOGITS
     carn
    0.07
    介入
    0.07
     الداخل
    0.07
     jeder
    0.06
    Dod
    0.06
     lod
    0.06
    ليل
    0.06
    괜
    0.06
    .CreateTable
    0.06
    簠
    0.06
    Activations Density 0.475%

    No Known Activations