© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 35057
    Prev
    Next
    INDEX
    Explanations

    JSON 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
    Negative Logits
    ãģ¾ãģĹãģ¦
    -0.07
    à¸ĵะ
    -0.06
    Ù°
    -0.06
    çŁ¾
    -0.06
    -0.06
    äºĴæį¢
    -0.06
    ack
    -0.06
    ÑĢег
    -0.06
    èĽĭ
    -0.05
    ÙİÙijØ©
    -0.05
    POSITIVE LOGITS
    åĬłæĭ¿å¤§
    0.08
    iasco
    0.08
    phia
    0.08
    trica
    0.08
    _WAKE
    0.08
    olidays
    0.08
    ifact
    0.07
    åĭĩå¾Ģ缴åīį
    0.07
    าà¸ļ
    0.07
    <|box_end|>
    0.07
    Activations Density 0.158%

    No Known Activations