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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 109606
    Prev
    Next
    INDEX
    Explanations

    foreign words

    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
     svm
    -0.08
     green
    -0.07
    inine
    -0.07
     validated
    -0.07
     Grinder
    -0.07
    osomal
    -0.07
    School
    -0.07
    -minute
    -0.07
    South
    -0.07
     drills
    -0.06
    POSITIVE LOGITS
     ресторан
    0.07
    对方
    0.07
    ến
    0.07
    当事人
    0.06
    بق
    0.06
     prolific
    0.06
     drama
    0.06
     الرجال
    0.06
     contempor
    0.06
    क
    0.06
    Activations Density 0.074%

    No Known Activations