Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 7320
    Prev
    Next
    INDEX
    Explanations

    Invention descriptions

    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
     eminent
    -0.07
     pá
    -0.07
    _vehicle
    -0.07
    .rb
    -0.07
    崎
    -0.06
     separ
    -0.06
     polish
    -0.06
     Ning
    -0.06
     dance
    -0.06
    .Byte
    -0.06
    POSITIVE LOGITS
    较为
    0.07
    _calibration
    0.07
    (properties
    0.07
    קדמי
    0.06
    Subscriber
    0.06
    Coords
    0.06
    Ѻ
    0.06
    WARDS
    0.06
    Data
    0.06
    FW
    0.06
    Activations Density 0.001%

    No Known Activations