© 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. 45956
    Prev
    Next
    INDEX
    Explanations

    shape, object, or structure

    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
    ukti
    -0.08
    egy
    -0.08
    ugier
    -0.07
    زش
    -0.07
    _HISTORY
    -0.07
    Fcn
    -0.07
    åĨĽä¸Ń
    -0.07
    dain
    -0.07
    ä¸ĢæĭĽ
    -0.07
    éĽĨä¸ŃçļĦ
    -0.07
    POSITIVE LOGITS
    ä¸ĬçļĦ
    0.10
    -wide
    0.09
    ä¸ĬçŃī
    0.08
     waarop
    0.08
    ä¸Ĭè¿Ľè¡Į
    0.08
    åĪĴåĪĨ为
    0.07
     пÑĢон
    0.07
     surface
    0.07
     layout
    0.07
    ä¸Ĭãģ§
    0.07
    Activations Density 0.091%

    No Known Activations