© 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. 38949
    Prev
    Next
    INDEX
    Explanations

    various data formats including numbers, characters, and abbreviations

    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
    ë²Į
    -0.08
    **|
    -0.08
    éĤ£åĦ¿
    -0.08
     ÙħÙĨÙĩÙħا
    -0.08
    æĪijä¿©
    -0.08
    å±Ģåī¯å±Ģéķ¿
    -0.08
    ä»ĸä¿©
    -0.08
    '),('
    -0.08
    [..
    -0.07
    erval
    -0.07
    POSITIVE LOGITS
    ãģ©ãĤĮãĤĤ
    0.09
    åħ¨éĥ½æĺ¯
    0.08
     semuanya
    0.08
    ãģĿãĤĮãģŀãĤĮ
    0.08
    æīĢæľīè¿ĻäºĽ
    0.08
     allemaal
    0.08
     all
    0.07
    åħ±è®¡
    0.07
    —all
    0.07
    çŃīçŃī
    0.07
    Activations Density 0.168%

    No Known Activations