© 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. 27755
    Prev
    Next
    INDEX
    Explanations

    mathematical variables and expressions

    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
    天å®ī
    -0.07
    acap
    -0.07
    geh
    -0.06
    uman
    -0.06
    deg
    -0.06
    uki
    -0.06
    ç»Ħç»Ħéķ¿
    -0.06
    UCA
    -0.06
     deg
    -0.06
    _logging
    -0.06
    POSITIVE LOGITS
    etta
    0.08
     Gam
    0.08
    详ç»ĨäºĨ解
    0.07
    awai
    0.07
    <Link
    0.07
    iné
    0.07
    ÑĤоÑĢиÑı
    0.07
    æĽ¿å°¼
    0.07
    kle
    0.07
    详ç»Ĩæııè¿°
    0.07
    Activations Density 0.003%

    No Known Activations