© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 75379
    Prev
    Next
    INDEX
    Explanations

    0

    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
    뉴
    -0.07
    _limits
    -0.07
    子ど
    -0.06
    雱
    -0.06
     placebo
    -0.06
     ledge
    -0.06
    Dto
    -0.06
     lanz
    -0.06
    _Execute
    -0.06
    殣
    -0.06
    POSITIVE LOGITS
    [M
    0.07
     bậc
    0.07
    .SQLException
    0.07
    бой
    0.07
    _interfaces
    0.07
    橱
    0.07
    眷
    0.07
    Recipient
    0.06
    ࿐
    0.06
    ersed
    0.06
    Activations Density 0.014%

    No Known Activations