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. 11-RESID-POST-AA
    6. 92416
    Prev
    Next
    INDEX
    Explanations

    Accidents/Incidents

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    stract
    -0.07
    lève
    -0.07
    Ƅ
    -0.07
     apprent
    -0.07
    oproject
    -0.07
     OCR
    -0.07
    previous
    -0.07
    ☪
    -0.07
     WIFI
    -0.07
    ————
    -0.06
    POSITIVE LOGITS
    .setViewportView
    0.07
     blot
    0.07
     Dow
    0.06
    情商
    0.06
     Behavioral
    0.06
     Begin
    0.06
    枢
    0.06
    תש
    0.06
    比较高
    0.06
    政法
    0.06
    Activations Density 0.231%

    No Known Activations