© 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. 87396
    Prev
    Next
    INDEX
    Explanations

    Salvador

    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
    互通
    -0.07
    土壤
    -0.07
     denial
    -0.06
     опыт
    -0.06
    تصميم
    -0.06
    验收
    -0.06
    received
    -0.06
    ʼ
    -0.06
    Outlet
    -0.06
    を持
    -0.06
    POSITIVE LOGITS
    读后
    0.08
     IonicModule
    0.07
     formulations
    0.07
     Scar
    0.07
    ฤษ
    0.07
    crafted
    0.07
     Photoshop
    0.07
    .Table
    0.07
     tracks
    0.07
    ❐
    0.07
    Activations Density 0.002%

    No Known Activations