© 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. 65456
    Prev
    Next
    INDEX
    Explanations

    numbers 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
    ngo
    -0.08
    onso
    -0.08
    ->_
    -0.08
    ecom
    -0.07
    onal
    -0.07
    éĹŃéŨ
    -0.07
    isco
    -0.07
    .backends
    -0.07
    xo
    -0.07
    rome
    -0.07
    POSITIVE LOGITS
    omot
    0.07
    å®Ī
    0.07
    éģĵ人
    0.07
    éŃĦ
    0.07
    artin
    0.07
    oples
    0.07
    ç¼Ń
    0.07
    aux
    0.06
    nels
    0.06
    itational
    0.06
    Activations Density 0.089%

    No Known Activations