© 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. 7741
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols in code

    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
    bior
    -0.07
    ØŃص
    -0.07
    å¡
    -0.07
    "><!--
    -0.07
     autrement
    -0.07
    agni
    -0.07
     Ñĥмол
    -0.07
    agÄĻ
    -0.07
    åħ¨åĽ½çļĦ
    -0.07
    æ¼Ĥ
    -0.06
    POSITIVE LOGITS
    æĪĸå°ij
    0.08
    мино
    0.08
    ilet
    0.07
    害ç¾ŀ
    0.07
    istol
    0.07
    IfNeeded
    0.07
     Lega
    0.07
    .sign
    0.07
     Casting
    0.07
    ç¾ŀ
    0.07
    Activations Density 0.003%

    No Known Activations