© 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. 1590
    Prev
    Next
    INDEX
    Explanations

    counting or measuring

    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
    åľ¨æ·±åľ³
    -0.08
    åľ¨åĮĹ京
    -0.08
    éķ¿è¾¾
    -0.08
    éĿ¢ç§¯è¾¾
    -0.07
     millennia
    -0.07
    ìŀIJìĿ¸
    -0.07
    åľ¨éŁ©åĽ½
    -0.07
    çİĭ大
    -0.07
     sid
    -0.06
    çİĭèĢħ
    -0.06
    POSITIVE LOGITS
    å¾Ģå¾Ģæĺ¯
    0.11
    éĢļ常æĺ¯
    0.10
    usually
    0.09
    åĽ¾çīĩæĪĸ
    0.08
    ä¸ĢèĪ¬æĺ¯
    0.08
    å¦Ĥæŀľæľī
    0.08
    å¾Ģå¾Ģä¼ļ
    0.08
    å¾Ģå¾Ģ
    0.08
    lest
    0.08
     varsa
    0.08
    Activations Density 0.010%

    No Known Activations