© 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. 15-RESID-POST-AA
    6. 1288
    Prev
    Next
    INDEX
    Explanations

    Showing how to understand

    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
     đạo
    -0.07
    \Command
    -0.07
    שמ
    -0.06
    ssi
    -0.06
    _listener
    -0.06
    🇶
    -0.06
    ẩm
    -0.06
    国资
    -0.06
    ひとつ
    -0.06
    .getCurrent
    -0.06
    POSITIVE LOGITS
    民居
    0.08
     histoire
    0.07
     smoother
    0.07
    开元
    0.07
    之初
    0.07
    激烈的
    0.07
    独特的
    0.07
    -gnu
    0.07
    ({↵
    0.07
     Gamb
    0.07
    Activations Density 0.064%

    No Known Activations