© 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. 56313
    Prev
    Next
    INDEX
    Explanations

    contrast conjunction

    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
    reich
    -0.09
    udad
    -0.08
    ithub
    -0.07
     fancy
    -0.07
    kast
    -0.07
    umpl
    -0.07
    wth
    -0.07
    觸
    -0.07
    é¢IJ
    -0.07
    .storage
    -0.07
    POSITIVE LOGITS
    ä½Ĩèĩ³å°ij
    0.08
    éĻ¤å¤ĸ
    0.07
    éĽª
    0.07
    ÑĮÑı
    0.07
    zz
    0.07
    ç
    0.06
    zu
    0.06
    å°ļåı¯
    0.06
    asses
    0.06
    orne
    0.06
    Activations Density 0.050%

    No Known Activations