© 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. 15386
    Prev
    Next
    INDEX
    Explanations

    chemical compound names

    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
    аниÑĨ
    -0.07
     ÑĢазÑĢе
    -0.07
    å¸ĺ
    -0.07
    ondi
    -0.07
    itty
    -0.07
    æĬij
    -0.07
    ameda
    -0.06
    ç¨į
    -0.06
    ndern
    -0.06
    æłı
    -0.06
    POSITIVE LOGITS
    æĸ°åĬłåĿ¡
    0.08
    acen
    0.08
    çĪµ
    0.07
    _GLOBAL
    0.07
    ih
    0.07
    gra
    0.07
    exo
    0.06
    以åıĬä¸İ
    0.06
    娲
    0.06
    asers
    0.06
    Activations Density 0.045%

    No Known Activations