© 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. 20873
    Prev
    Next
    INDEX
    Explanations

    Lévy flights, stable distribution, power law

    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
    æĨ¬
    -0.09
    ½Ķ
    -0.09
    èĥŀèĥİ
    -0.09
    åIJijèį£
    -0.08
    Automatic
    -0.08
    éĶ¦ä¸Ĭæ·»èĬ±
    -0.08
    czyk
    -0.08
    .codes
    -0.08
    æı´æľĿ
    -0.08
    空éĹ´ç«Ļ
    -0.08
    POSITIVE LOGITS
    åŀ
    0.07
     shocks
    0.07
     outliers
    0.07
    åĪĨå¸ĥ
    0.07
     sed
    0.07
    å°¾éĥ¨
    0.07
     shock
    0.07
     Wol
    0.07
     Sed
    0.07
    åĪĨæķ£
    0.07
    Activations Density 0.007%

    No Known Activations