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. 21641
    Prev
    Next
    INDEX
    Explanations

    gravity

    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
     dön
    -0.07
    _install
    -0.07
     motivational
    -0.07
     imperialism
    -0.07
     kell
    -0.07
     hemos
    -0.07
     farklı
    -0.07
    탯
    -0.07
     promoter
    -0.07
    🍱
    -0.07
    POSITIVE LOGITS
    иков
    0.07
    rias
    0.07
     $.
    0.06
    rated
    0.06
     wipes
    0.06
     shadow
    0.06
    ution
    0.06
     meeting
    0.06
    那些
    0.06
     Sarah
    0.06
    Activations Density 0.004%

    No Known Activations