© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 50046
    Prev
    Next
    INDEX
    Explanations

    beneficial or once

    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
    ovil
    -0.08
    鸥
    -0.07
    åĪĨå¤ĸ
    -0.07
    .fake
    -0.06
    ceeded
    -0.06
    空ä¸ŃçļĦ
    -0.06
    ivot
    -0.06
    _spec
    -0.06
    天æĺŁ
    -0.06
    ixmap
    -0.06
    POSITIVE LOGITS
    åı¯èĥ½åľ¨
    0.09
    åı¯èĥ½å¯¹
    0.09
     ÙħÙħÚ©ÙĨ
    0.08
    åIJ«ç¬ij
    0.08
    çİ°åľ¨çľĭæĿ¥
    0.08
    ä¹Łåı¯èĥ½æĺ¯
    0.08
    åı¯èĥ½å°±
    0.08
    may
    0.08
    ä¹Łåı¯èĥ½
    0.08
    à¸Ńาà¸Ī
    0.08
    Activations Density 0.067%

    No Known Activations