© 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. 43660
    Prev
    Next
    INDEX
    Explanations

    catalyzed

    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
    æ·±åĪ»çļĦåį°è±¡
    -0.07
    æīĢ使çĶ¨çļĦ
    -0.07
    åĮĸ管çIJĨ
    -0.07
    ç»·
    -0.07
    .outer
    -0.06
    æłĩéħį
    -0.06
    à¹Ģลย
    -0.06
    íĥ
    -0.06
    ancy
    -0.06
    姿
    -0.06
    POSITIVE LOGITS
    irected
    0.08
    uced
    0.08
    ä¸ĭçļĦ
    0.08
     történ
    0.08
    lore
    0.08
    anced
    0.07
    éĽªå³°
    0.07
    ourd
    0.07
    .examples
    0.07
    doch
    0.07
    Activations Density 0.019%

    No Known Activations