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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 75571
    Prev
    Next
    INDEX
    Explanations

    say "copy"

    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
    땅
    -0.07
    茈
    -0.07
    .Are
    -0.07
    すこと
    -0.06
    pike
    -0.06
    تر
    -0.06
    蠲
    -0.06
    Propagation
    -0.06
     İn
    -0.06
     Bởi
    -0.06
    POSITIVE LOGITS
    要么
    0.08
    OTHER
    0.07
    .Entry
    0.07
     exhib
    0.07
    意见建议
    0.07
    Sent
    0.07
    _TRANSFER
    0.07
    奖学金
    0.07
    优异
    0.07
    融
    0.07
    Activations Density 0.008%

    No Known Activations