© 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. 45981
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and programming constructs

    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
    enni
    -0.07
    ת×Ļ
    -0.07
    åİĭ缩
    -0.06
    ÏģÎŃ
    -0.06
    _minimum
    -0.06
    æ»ļ
    -0.06
    è´«
    -0.06
    igi
    -0.06
    åľ¨å½ĵåīį
    -0.06
    ice
    -0.06
    POSITIVE LOGITS
    度æķ°
    0.10
    Ỽm
    0.09
     HALF
    0.09
    Sym
    0.09
    åįĬ个
    0.08
    ngle
    0.08
     linspace
    0.08
    half
    0.08
    对称
    0.08
     half
    0.08
    Activations Density 0.002%

    No Known Activations