© 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. 38687
    Prev
    Next
    INDEX
    Explanations

    cost and size judgments

    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
    æĹłéĻIJ
    -0.08
    å°±æĺ¯ä¸Ģç§į
    -0.08
     inscr
    -0.07
    ä¸įèĥ½å®Įåħ¨
    -0.07
     imperfect
    -0.07
    åIJijæ³ķéĻ¢
    -0.07
    rekt
    -0.07
    çļ®ä¹¦
    -0.07
    çļĦè¿Ļç§į
    -0.07
    å«Ĥ
    -0.07
    POSITIVE LOGITS
     (>
    0.08
    åī¯ä¸»å¸Ń
    0.07
    _MOD
    0.07
    erset
    0.07
    åĽ½åĨħ
    0.06
    端çļĦ
    0.06
    ér
    0.06
    ä¼ģä¸ļæĸ°éĹ»
    0.06
    (~
    0.06
    estone
    0.06
    Activations Density 0.017%

    No Known Activations