© 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. 7836
    Prev
    Next
    INDEX
    Explanations

    alpha, α, splitting, track, detectors, tribe

    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
    åħ³äºĨ
    -0.08
    é¢łåĢĴ
    -0.08
    èĻļå¿ĥ
    -0.07
    å¨ĺåŃIJ
    -0.07
    issy
    -0.07
    çļĪ
    -0.07
    大浪
    -0.07
    ä¸ĢæĹł
    -0.07
    åĶı
    -0.07
    .Serve
    -0.07
    POSITIVE LOGITS
    è£Ĥ
    0.08
    æĪIJçĨŁ
    0.07
     cigar
    0.07
    å®ļæľŁè¿Ľè¡Į
    0.07
    bung
    0.07
    è£Ĥåıĺ
    0.07
    åĪĨè£Ĥ
    0.07
    æĺ¯è¿Ļ个
    0.07
     eject
    0.07
    æĪIJçĨŁçļĦ
    0.07
    Activations Density 0.003%

    No Known Activations