© 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. 20168
    Prev
    Next
    INDEX
    Explanations

    ratios and relative numbers

    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
    é¢ł
    -0.07
    mina
    -0.07
    çĶ¨æĪ·çļĦéľĢæ±Ĥ
    -0.07
    èĹ©
    -0.07
    åı¯è´µ
    -0.07
     paraph
    -0.07
    Pa
    -0.07
    ä¸ĢéĹ®
    -0.06
    Ju
    -0.06
    mm
    -0.06
    POSITIVE LOGITS
    edly
    0.10
    xon
    0.08
    cto
    0.08
    centage
    0.08
    .gov
    0.08
    åĮĸ
    0.08
     ratios
    0.07
    fat
    0.07
    ç¨ĭ度çļĦ
    0.07
    ç§ijæĬĢåıijå±ķæľīéĻIJåħ¬åı¸
    0.07
    Activations Density 0.019%

    No Known Activations