© 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. 47801
    Prev
    Next
    INDEX
    Explanations

    genus 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
    dera
    -0.09
    imoni
    -0.08
    esak
    -0.07
    åĹħ
    -0.07
    rira
    -0.07
    æĪIJå¹´
    -0.07
    uges
    -0.07
    ÃĩO
    -0.07
    ira
    -0.07
    ноÑģ
    -0.07
    POSITIVE LOGITS
    çij
    0.07
    BlockSize
    0.07
    oun
    0.07
    èݽ
    0.07
    å»
    0.07
    西éĥ¨
    0.06
    å¾Ļ
    0.06
    itz
    0.06
     kun
    0.06
    èįĨ
    0.06
    Activations Density 0.010%

    No Known Activations