© 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. 10848
    Prev
    Next
    INDEX
    Explanations

    index

    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
    andalone
    -0.07
    vet
    -0.07
    è¡Įä¹ĭ
    -0.06
     ._
    -0.06
    hle
    -0.06
    è¡ĮåĬ¨èµ·æĿ¥
    -0.06
    itere
    -0.06
     Hood
    -0.06
    iter
    -0.06
    IFIER
    -0.06
    POSITIVE LOGITS
    åħ¬åı¸çŃī
    0.09
    æ´»åĬ¨çŃī
    0.09
     thereafter
    0.08
    为è¾ħ
    0.08
    ×ķ×ķת
    0.08
    staking
    0.08
    ä¸İä¹ĭ
    0.08
     thereof
    0.08
    лаго
    0.07
     altrettanto
    0.07
    Activations Density 0.225%

    No Known Activations