© 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. 25830
    Prev
    Next
    INDEX
    Explanations

    questions about things

    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
     hopefully
    -0.08
    åı¯èĥ½æĺ¯åĽłä¸º
    -0.07
     presumably
    -0.07
    pero
    -0.06
    åĴĢ
    -0.06
    лона
    -0.06
    æľĢæĸ°ç«łèĬĤ
    -0.06
    å¾Īåı¯èĥ½æĺ¯
    -0.06
    åĽ½åħ¬
    -0.06
     probably
    -0.06
    POSITIVE LOGITS
     ever
    0.12
    æľīä»»ä½ķ
    0.11
     EVER
    0.10
     acaso
    0.10
    å°±ä¸Ģå®ļ
    0.10
    å°±è¿Ļæł·
    0.09
    羣çļĦæľī
    0.09
    å°±éĢĻ樣
    0.09
    åı¯åIJ¦
    0.09
    è¶³å¤Ł
    0.09
    Activations Density 0.076%

    No Known Activations