© 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. 46339
    Prev
    Next
    INDEX
    Explanations

    carbene or carbenes

    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
    inari
    -0.08
    IMIT
    -0.07
    ARGS
    -0.07
    olni
    -0.07
    ugs
    -0.07
     Tua
    -0.07
    rove
    -0.06
    ForObject
    -0.06
    speech
    -0.06
    éĢĤ
    -0.06
    POSITIVE LOGITS
    åij¼åij¼
    0.07
    ä»·æł¼è¡Įæĥħ
    0.07
    enger
    0.07
     Bookmark
    0.07
    ặng
    0.07
    åĴ³åĴ³
    0.06
    족
    0.06
    Ặ
    0.06
    åħ°èĬ±
    0.06
    eph
    0.06
    Activations Density 0.017%

    No Known Activations