© 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. 13097
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas

    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
    astica
    -0.07
    iesel
    -0.07
    upas
    -0.07
    hurst
    -0.07
    çIJĨ
    -0.07
     обÑıзаÑĤелÑĮном
    -0.07
    kee
    -0.06
    olen
    -0.06
    éĻIJ度
    -0.06
     Aspe
    -0.06
    POSITIVE LOGITS
    raven
    0.07
    è¡ĮåĪĹ
    0.07
    Ìģ
    0.07
    åĮł
    0.07
    дÑİ
    0.06
    ä¹į
    0.06
    ÑıÑĢ
    0.06
    ierz
    0.06
    èĢ½æIJģ
    0.06
    bÃŃ
    0.06
    Activations Density 0.007%

    No Known Activations