© 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. 56104
    Prev
    Next
    INDEX
    Explanations

    probability of

    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
    estream
    -0.08
    alker
    -0.07
    åĬ¨éĿĻ
    -0.07
    _UNDEFINED
    -0.07
    æĬ¥åIJįåħ¥åı£
    -0.07
    eners
    -0.07
    onsin
    -0.07
    getParam
    -0.07
    .batch
    -0.07
    Quiet
    -0.07
    POSITIVE LOGITS
    emar
    0.07
    æģ°å¥½
    0.07
    å¾Ĵ
    0.07
    åħ¶ä¸Ń
    0.07
     probability
    0.07
    大ä¹ī
    0.06
    bez
    0.06
    ante
    0.06
    nev
    0.06
    nox
    0.06
    Activations Density 0.021%

    No Known Activations