© 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. 28353
    Prev
    Next
    INDEX
    Explanations

    technical terms and punctuation

    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
    ipel
    -0.07
    ä¸Ģå¸Ĩé£İ顺
    -0.06
    ä¸Ģç§į
    -0.06
    mals
    -0.06
    hui
    -0.06
     fall
    -0.06
     Andersen
    -0.06
    colar
    -0.06
    èľľ
    -0.06
    èĭ¥èĥ½
    -0.06
    POSITIVE LOGITS
    zit
    0.08
    ãĤªãĤ¤
    0.08
    æģįæĥļ
    0.07
    éĩijåŃIJ
    0.07
    acha
    0.07
    çļĦé»Ħéĩij
    0.07
    éķĤ
    0.07
    ä½łåij¢
    0.07
     tá»±u
    0.07
    æĹłä¸Ĭ
    0.07
    Activations Density 0.300%

    No Known Activations