© 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. 28942
    Prev
    Next
    INDEX
    Explanations

    semicolon statements

    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
     nameof
    -0.07
    åħ¬åı¸åľ°åĿĢ
    -0.07
    zac
    -0.07
    äºĭåħĪ
    -0.07
    waan
    -0.07
    önen
    -0.07
    .lua
    -0.07
    omie
    -0.06
    _MAXIMUM
    -0.06
    ohen
    -0.06
    POSITIVE LOGITS
    iné
    0.07
    èįī
    0.07
    gal
    0.06
    PURE
    0.06
    lop
    0.06
    rat
    0.06
    æĥ¹
    0.06
    walt
    0.06
    èĭĽ
    0.06
    æł¹æį®
    0.06
    Activations Density 0.074%

    No Known Activations