© 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. 11268
    Prev
    Next
    INDEX
    Explanations

    ON PK

    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
    еÑĤо
    -0.07
    纲
    -0.07
    =./
    -0.07
    綱
    -0.07
    éįĭ
    -0.07
    ink
    -0.06
     '`
    -0.06
     dispar
    -0.06
    头åĥı
    -0.06
    çļĦåį±éĻ©
    -0.06
    POSITIVE LOGITS
    åħ³æ³¨æĪij们
    0.07
    feh
    0.07
    orp
    0.07
    åIJ¦
    0.07
    esti
    0.07
    DEX
    0.07
    以å¤ĸ
    0.07
    otify
    0.06
    å¾Ļ
    0.06
    marshall
    0.06
    Activations Density 0.052%

    No Known Activations