© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 48540
    Prev
    Next
    INDEX
    Explanations

    connected to

    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
    æ¿Ģ
    -0.07
    并æıIJ交
    -0.07
    åĩıéĩı
    -0.07
    èĪĴ
    -0.07
    à²Ĥದ
    -0.06
    ç²¾åĩĨ
    -0.06
    æķ´é½IJ
    -0.06
     competition
    -0.06
    çªĹåı£
    -0.06
    rak
    -0.06
    POSITIVE LOGITS
     via
    0.12
    è¿ŀéĢļ
    0.12
     connectivity
    0.12
    via
    0.11
     Via
    0.11
    -connected
    0.11
    connected
    0.11
     connected
    0.11
    .connected
    0.10
    _via
    0.10
    Activations Density 0.011%

    No Known Activations