© 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. 11-RESID-POST-AA
    6. 75370
    Prev
    Next
    INDEX
    Explanations

    astronomy data

    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
     var
    -0.07
     StringSplitOptions
    -0.07
     מהווה
    -0.07
     maxValue
    -0.06
    엨
    -0.06
     declaring
    -0.06
    (dom
    -0.06
    "))
    ↵
    -0.06
     derp
    -0.06
    urities
    -0.06
    POSITIVE LOGITS
     indoor
    0.08
    Caps
    0.07
     humane
    0.07
    .about
    0.07
    /how
    0.07
    lon
    0.06
     southwestern
    0.06
    Net
    0.06
    'Connor
    0.06
    firstName
    0.06
    Activations Density 0.023%

    No Known Activations