© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 15831
    Prev
    Next
    INDEX
    Explanations

    numbers and calculations

    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
    æ»´æ°´
    -0.09
    plib
    -0.08
    çļĦæŃ»
    -0.08
    -await
    -0.08
    plit
    -0.08
    staw
    -0.07
    iclet
    -0.07
    _helpers
    -0.07
    PLIT
    -0.07
    à¸Ķีà¸ķ
    -0.07
    POSITIVE LOGITS
     hy
    0.09
    æī
    0.06
    isNaN
    0.06
    夺
    0.06
    infer
    0.06
    éĩįåŀĭ
    0.06
     usual
    0.06
    chez
    0.06
    argo
    0.06
    hy
    0.06
    Activations Density 0.026%

    No Known Activations