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. 109544
    Prev
    Next
    INDEX
    Explanations

    ctype

    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
    孩童
    -0.07
     책임
    -0.07
    뇌
    -0.07
     codes
    -0.07
    ᶰ
    -0.07
    -email
    -0.06
    דיון
    -0.06
    igmoid
    -0.06
    ious
    -0.06
    黎
    -0.06
    POSITIVE LOGITS
     lows
    0.07
    /import
    0.07
    重心
    0.07
     reporting
    0.06
     flare
    0.06
    ению
    0.06
     DependencyProperty
    0.06
    𝘷
    0.06
    Mgr
    0.06
     trustworthy
    0.06
    Activations Density 0.001%

    No Known Activations