© 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. 40872
    Prev
    Next
    INDEX
    Explanations

    propagation nonlinear generation

    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
    è¸ı
    -0.08
    æŀIJ
    -0.07
     tarn
    -0.07
    elts
    -0.07
    ots
    -0.07
     Svens
    -0.07
    çīĮ
    -0.06
     municip
    -0.06
     ore
    -0.06
     turno
    -0.06
    POSITIVE LOGITS
    izzi
    0.09
    æļ´
    0.09
    æīĵåľ¨
    0.08
    istol
    0.08
    æīĵãģ¡
    0.08
    hoff
    0.08
    çİĭéĩij
    0.07
    .jet
    0.07
    ä¹ĭçİĭ
    0.07
     verl
    0.07
    Activations Density 0.001%

    No Known Activations