© 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. 61500
    Prev
    Next
    INDEX
    Explanations

    Quotation Marks

    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
     Site
    -0.08
     Picasso
    -0.08
    (protocol
    -0.07
     Services
    -0.07
    脱贫攻坚
    -0.07
    ocrates
    -0.07
    表明
    -0.07
    Cliente
    -0.07
    南非
    -0.07
     المحلية
    -0.07
    POSITIVE LOGITS
     vulner
    0.07
     Trou
    0.07
     наход
    0.07
    )!=
    0.06
     Kepler
    0.06
     감
    0.06
    ."<
    0.06
     Fav
    0.06
     dial
    0.06
    ރ
    0.06
    Activations Density 0.133%

    No Known Activations