© 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. 50677
    Prev
    Next
    INDEX
    Explanations

    aka 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
    éĥ½æĺ¯æĪij
    -0.07
    Assembler
    -0.07
    uali
    -0.07
    uetooth
    -0.07
    åݲ
    -0.07
    eldorf
    -0.07
     ################################################
    -0.07
    éĿ¢æİĪ
    -0.07
    endenza
    -0.07
    ================================================================================
    -0.07
    POSITIVE LOGITS
    ä¸ĭåIJĮ
    0.13
    its
    0.07
    åıĸåħ¶
    0.07
    åħ¶ä¸º
    0.06
    itmap
    0.06
    天çĦ¶çļĦ
    0.06
    åĪĻ该
    0.06
    stelle
    0.06
    Th
    0.06
    计åĪĴçļĦ
    0.06
    Activations Density 1.158%

    No Known Activations