© 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. 85500
    Prev
    Next
    INDEX
    Explanations

    environment

    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
    当事人
    -0.07
     double
    -0.07
     compressed
    -0.07
    做什么
    -0.07
    )↵↵↵↵
    -0.06
    本人
    -0.06
    .Display
    -0.06
    edin
    -0.06
     PD
    -0.06
     holder
    -0.06
    POSITIVE LOGITS
     unix
    0.07
     fotoğ
    0.07
    .reference
    0.07
     rentals
    0.07
    vents
    0.07
    넼
    0.07
    呔
    0.07
    宧
    0.07
    ReLU
    0.07
    .Db
    0.06
    Activations Density 0.022%

    No Known Activations