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. 15-RESID-POST-AA
    6. 27831
    Prev
    Next
    INDEX
    Explanations

    copyright and permissions

    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
    ☾
    -0.07
    dash
    -0.07
    ☰
    -0.07
    央
    -0.07
    _counts
    -0.06
    YT
    -0.06
     contro
    -0.06
    Master
    -0.06
     bell
    -0.06
    ҷ
    -0.06
    POSITIVE LOGITS
     Incorpor
    0.07
    -----↵
    0.07
     politely
    0.07
    passes
    0.07
    丫头
    0.07
     purchase
    0.07
     nailed
    0.06
    所以
    0.06
    投影
    0.06
    _protocol
    0.06
    Activations Density 0.010%

    No Known Activations