© 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. 24632
    Prev
    Next
    INDEX
    Explanations

    d

    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
    <App
    -0.07
    =params
    -0.07
    (key
    -0.06
    可以更好
    -0.06
    兼顾
    -0.06
     ng
    -0.06
    .bat
    -0.06
    不容易
    -0.06
    Pow
    -0.06
     inn
    -0.06
    POSITIVE LOGITS
    olynomial
    0.07
     defiant
    0.07
    涨幅
    0.07
     провед
    0.07
    >",↵
    0.07
    ении
    0.07
    trial
    0.07
    部门
    0.07
    тель
    0.07
     règle
    0.07
    Activations Density 0.000%

    No Known Activations