© 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. 20079
    Prev
    Next
    INDEX
    Explanations

    order relation

    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
    изи
    -0.08
    åıĭæĥħéĵ¾æİ¥
    -0.07
    ož
    -0.07
    çŁŃ缺
    -0.07
    γη
    -0.07
    subs
    -0.07
    åīĬåĩı
    -0.06
    ÈĻti
    -0.06
    æĬķ稿éĤ®ç®±
    -0.06
    èģ¯
    -0.06
    POSITIVE LOGITS
    è¾Ī
    0.08
     precedence
    0.08
    Chron
    0.08
     ÑĥÑģп
    0.07
    chron
    0.07
     dates
    0.07
     chronological
    0.07
    oser
    0.07
    é«ĺç§ij
    0.07
     chron
    0.07
    Activations Density 0.009%

    No Known Activations