© 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. 19-RESID-POST-AA
    11. 75638
    Prev
    Next
    INDEX
    Explanations

    weight loss

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ')+
    -0.07
     vscode
    -0.07
     full
    -0.07
     bastard
    -0.07
     live
    -0.06
    getLast
    -0.06
    Customer
    -0.06
    (Book
    -0.06
     soul
    -0.06
    띈
    -0.06
    POSITIVE LOGITS
    óg
    0.07
     sẻ
    0.07
     América
    0.07
    inton
    0.07
     Incre
    0.07
     Displays
    0.07
    aminer
    0.07
    uan
    0.06
    _LOADING
    0.06
    asha
    0.06
    Activations Density 0.179%

    No Known Activations