© 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. 24874
    Prev
    Next
    INDEX
    Explanations

    Expressing feelings

    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
     zwe
    -0.08
     earnest
    -0.07
    _iv
    -0.07
     Cookbook
    -0.07
     foster
    -0.07
     Negro
    -0.07
     epit
    -0.07
    明ら
    -0.07
     PdfP
    -0.07
    贴近
    -0.07
    POSITIVE LOGITS
    olut
    0.07
    putation
    0.07
     输
    0.07
     Тур
    0.07
    only
    0.07
    yecto
    0.07
    多少钱
    0.07
    Quite
    0.07
     Rut
    0.07
    ומי
    0.07
    Activations Density 0.082%

    No Known Activations