© 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. 62197
    Prev
    Next
    INDEX
    Explanations

    connections of numbers to 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
    ostro
    -0.08
    å®Ŀå®Ŀ们
    -0.07
    kampf
    -0.07
    ripp
    -0.07
    autop
    -0.07
    æĿ±è¥¿
    -0.07
    entered
    -0.06
    æĿ¥ä¸įåıĬ
    -0.06
    è¿Ļæĺ¯åľ¨
    -0.06
    åIJĪåIJĮ约å®ļçļĦ
    -0.06
    POSITIVE LOGITS
    åıĪ
    0.07
    _PARSE
    0.07
    esak
    0.07
    åıĪåĥı
    0.07
    åıĪä¼ļ
    0.07
    åıĪåı¯
    0.07
    Ľ
    0.06
     zase
    0.06
    åħĭæŀĹ
    0.06
    åıĪåı¯ä»¥
    0.06
    Activations Density 0.026%

    No Known Activations