© 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. 19995
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and symbols

    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
    èĢģåıĭ
    -0.08
    ulus
    -0.07
     Candid
    -0.06
    åħīè¾ī
    -0.06
    åı¥åı¥
    -0.06
    ostat
    -0.06
    sko
    -0.06
    æłij人
    -0.06
    è¸ıè¸ıå®ŀ
    -0.06
    ulon
    -0.06
    POSITIVE LOGITS
    uille
    0.07
    vertime
    0.07
    åĽĽåĪĨ
    0.07
    ذب
    0.07
    کت
    0.07
    anmar
    0.07
    requency
    0.07
    usin
    0.07
    tas
    0.07
     unmarried
    0.07
    Activations Density 0.001%

    No Known Activations