© 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. 43884
    Prev
    Next
    INDEX
    Explanations

    first variant

    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
    ä¸ĭ表
    -0.08
    çŁ³éŨ
    -0.07
    æ¶İ
    -0.06
    æł¼æĭī
    -0.06
    ábado
    -0.06
    åīįåĽŀ
    -0.06
    èĩªè¯Ń
    -0.06
    áĥ§
    -0.06
    auf
    -0.06
    enia
    -0.06
    POSITIVE LOGITS
    èĢ³
    0.08
    ocha
    0.08
    isky
    0.07
    æĥħåĨµè¯´æĺİ
    0.07
    åıªæĺ¯ä¸Ģ
    0.07
    åıªæĺ¯
    0.07
     bando
    0.07
    |#
    0.07
    uret
    0.07
    ç¥ī
    0.07
    Activations Density 0.001%

    No Known Activations