© 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. 8153
    Prev
    Next
    INDEX
    Explanations

    comment syntax and separators

    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
    ously
    -0.08
    erschein
    -0.07
    大ä¸ĸçķĮ
    -0.07
    å«£
    -0.07
    æĿ¥è¶Ĭ
    -0.07
    itarian
    -0.07
    ettino
    -0.07
    iker
    -0.07
    à¸īะà¸Ļัà¹īà¸Ļ
    -0.07
     ç§ģ
    -0.07
    POSITIVE LOGITS
    APO
    0.08
    cade
    0.07
    lsi
    0.07
    éma
    0.07
    ç´ł
    0.07
    æıIJ
    0.06
    ัว
    0.06
    èĤ´
    0.06
    ä¾Ī
    0.06
    gaard
    0.06
    Activations Density 0.017%

    No Known Activations