© 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. 62264
    Prev
    Next
    INDEX
    Explanations

    new

    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
    哺
    -0.07
    Ĩ
    -0.07
    dı
    -0.07
    (primary
    -0.07
    (cols
    -0.07
    hm
    -0.07
    隼
    -0.07
    .audio
    -0.06
    哪
    -0.06
    휨
    -0.06
    POSITIVE LOGITS
     racked
    0.08
     neighbors
    0.07
     salarié
    0.07
    _types
    0.07
     VE
    0.06
     Corporation
    0.06
     américain
    0.06
    thrown
    0.06
     Ottoman
    0.06
    と思っていた
    0.06
    Activations Density 0.046%

    No Known Activations