© 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. 56667
    Prev
    Next
    INDEX
    Explanations

    oxidation state or valence

    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
    WithTag
    -0.08
     ÑĤÑĢо
    -0.07
    ÙĪÙħÙĬ
    -0.07
    hari
    -0.07
    zlich
    -0.07
    uments
    -0.07
     frequ
    -0.07
     KHO
    -0.07
    ики
    -0.07
    人æīĭ
    -0.07
    POSITIVE LOGITS
    æĢģ
    0.09
    åĨĻåľ¨
    0.07
    è¿ĺåİŁ
    0.07
    state
    0.07
    åĨĻæ³ķ
    0.07
     Chatt
    0.07
    oxid
    0.07
    вал
    0.07
     Fe
    0.07
    ilitary
    0.07
    Activations Density 0.004%

    No Known Activations