© 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. 9733
    Prev
    Next
    INDEX
    Explanations

    what happens when

    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
    anmar
    -0.09
    ijos
    -0.08
    ibur
    -0.07
     probably
    -0.07
    urts
    -0.07
    usto
    -0.07
    coon
    -0.07
    igs
    -0.06
    any
    -0.06
    ewan
    -0.06
    POSITIVE LOGITS
     же
    0.08
     if
    0.08
     cases
    0.07
    ä¸ĩä¸Ģ
    0.07
    _ENCOD
    0.07
    äºİä»Ĭå¹´
    0.07
    æĺİæĺİ
    0.07
     hvis
    0.07
    .cuda
    0.07
     gdy
    0.07
    Activations Density 0.017%

    No Known Activations