© 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. 49403
    Prev
    Next
    INDEX
    Explanations

    following link, code, modules, articles

    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
    umbo
    -0.07
    æ´²
    -0.07
    ç¹¼çºĮéĸ±è®Ģ
    -0.07
    è¿Ļ家ä¼Ļ
    -0.06
    isNaN
    -0.06
    æ®ĭ奥
    -0.06
    _unset
    -0.06
     Midlands
    -0.06
     Humph
    -0.06
    ilion
    -0.06
    POSITIVE LOGITS
    arine
    0.08
    hana
    0.07
    ÙĪتر
    0.07
    ä¸Ĭ交
    0.07
    FetchRequest
    0.07
    é¡¹çĽ®è¿Ľè¡Į
    0.07
    人ä¸Ģ
    0.06
    atsby
    0.06
    inverse
    0.06
    ä¸įæīĵ
    0.06
    Activations Density 0.007%

    No Known Activations