© 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. 41658
    Prev
    Next
    INDEX
    Explanations

    CV, psalm, currency

    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
    ouncer
    -0.07
    roke
    -0.06
    ONOM
    -0.06
    åı¥è¯Ŀ说
    -0.06
    é¡¹çĽ®æī¿åĬŀåįķä½į
    -0.06
    ...*
    -0.06
    CION
    -0.06
    tpl
    -0.06
    OrUpdate
    -0.06
    çĻ¾èįī
    -0.06
    POSITIVE LOGITS
    ife
    0.08
    ãģ§ãĤĤãģªãģĦ
    0.07
    ×ij׾
    0.07
    ç±»çŃī
    0.07
    éĿĴè¡£
    0.07
    æĢ¡
    0.07
    -like
    0.07
    वाल
    0.06
    as
    0.06
    аÑģÑĤо
    0.06
    Activations Density 0.176%

    No Known Activations