© 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. 20043
    Prev
    Next
    INDEX
    Explanations

    groupoids, extensions, diagram, operates, sets, metrics, boundary

    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
    apus
    -0.08
    cade
    -0.07
    _mB
    -0.07
    á»Ī
    -0.07
    apper
    -0.07
    olu
    -0.07
    à¸ľ
    -0.07
    nado
    -0.07
    åħ¶ä»ĸåªĴä½ĵ
    -0.07
    asco
    -0.07
    POSITIVE LOGITS
    áh
    0.07
    cki
    0.07
    à¸ķร
    0.06
    .yahoo
    0.06
     HM
    0.06
    åĴĮæĶ¹è¿Ľ
    0.06
    uez
    0.06
    æŀĹåŃIJ
    0.06
    -hidden
    0.06
     Hos
    0.06
    Activations Density 0.022%

    No Known Activations