© 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. 110245
    Prev
    Next
    INDEX
    Explanations

    calculate/determine

    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
     месте
    -0.07
    除此之外
    -0.07
    🎢
    -0.07
     magnets
    -0.07
     נוס
    -0.06
    _corpus
    -0.06
    野外
    -0.06
     стало
    -0.06
    社会效益
    -0.06
    🅖
    -0.06
    POSITIVE LOGITS
     Need
    0.08
    imple
    0.07
    ourses
    0.07
     Main
    0.07
    罪
    0.07
    nore
    0.07
     Necessary
    0.07
     sponsors
    0.07
    constructor
    0.07
     Dinner
    0.07
    Activations Density 0.012%

    No Known Activations