© 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. 40579
    Prev
    Next
    INDEX
    Explanations

    rounding, precision, or formatting

    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
    åıªæĺ¯æĥ³
    -0.08
    imba
    -0.08
    landa
    -0.08
    åıªæĥ³
    -0.07
    éļħ
    -0.07
    çĻ¾åıĺ
    -0.07
    çŁ¥éģĵæĪij
    -0.07
    æĪIJåIJį
    -0.07
    ç´¯äºĨ
    -0.07
     NotImplemented
    -0.07
    POSITIVE LOGITS
     arro
    0.08
     rounding
    0.08
    èĪį
    0.08
     окÑĢÑĥг
    0.07
    ä¾Ŀçħ§
    0.07
     err
    0.07
    .fits
    0.07
    åĪ¤æĸŃ
    0.06
    Ascii
    0.06
     bin
    0.06
    Activations Density 0.008%

    No Known Activations