© 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. 20101
    Prev
    Next
    INDEX
    Explanations

    special characters followed by words

    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
    /or
    -0.07
    inz
    -0.06
    ée
    -0.06
    à¥įरà¥Ģ
    -0.06
    oux
    -0.06
     Ganze
    -0.06
    haps
    -0.06
    ips
    -0.06
    atas
    -0.06
    åıĪä½ķ
    -0.06
    POSITIVE LOGITS
    ï¸İ
    0.16
    ï¸ı
    0.09
    缸è¾ħ缸æĪIJ
    0.09
    åIJĦç§įåIJĦæł·
    0.09
    æ¯Ľæ³½ä¸ľæĢĿæĥ³
    0.09
    ä¸įæĥĬ
    0.09
    leÅŁ
    0.08
    zinho
    0.08
    俱ä¹IJéĥ¨
    0.08
    aise
    0.07
    Activations Density 0.043%

    No Known Activations