© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 29245
    Prev
    Next
    INDEX
    Explanations

    code structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    istine
    -0.07
    å©¢
    -0.07
    NCY
    -0.07
    <|box_end|>
    -0.07
    peater
    -0.07
    accom
    -0.07
    IDO
    -0.07
    ساÙĨÛĮ
    -0.07
    arty
    -0.07
    ichel
    -0.07
    POSITIVE LOGITS
    æľīäºĨ
    0.08
    åºĶè¯¥åľ¨
    0.07
    ossal
    0.07
    æ¸
    0.07
    yms
    0.07
     Pruitt
    0.06
    íĽĪ
    0.06
    æ©
    0.06
    InitialState
    0.06
     offs
    0.06
    Activations Density 0.091%

    No Known Activations