© 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. 29546
    Prev
    Next
    INDEX
    Explanations

    Continue reading

    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
     wunderbar
    -0.06
    æĦģ
    -0.06
    ç»ĵæł¸
    -0.06
    æ¡ĥèĬ±
    -0.06
     aforementioned
    -0.06
    æ»
    -0.06
    å¾·æĭī
    -0.06
    uv
    -0.06
    ephy
    -0.06
    -t
    -0.06
    POSITIVE LOGITS
    Ñĺи
    0.08
    bang
    0.08
    istan
    0.07
    é«ĺç§ij
    0.07
    NullOr
    0.07
    ä¸ĭéĿ¢æĺ¯å°ıç¼ĸ
    0.07
    lsi
    0.07
    egah
    0.07
    pei
    0.07
    è¿ĶåĽŀ顶éĥ¨
    0.07
    Activations Density 0.014%

    No Known Activations