© 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. 22187
    Prev
    Next
    INDEX
    Explanations

    Zeno effect

    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
     Stras
    -0.08
    éħİ
    -0.08
    æł©æł©
    -0.07
    äºijå±±
    -0.07
    ayan
    -0.07
    ockey
    -0.07
    åľ¨å»º
    -0.07
    adre
    -0.06
    aton
    -0.06
    åıªæĺ¯æĥ³
    -0.06
    POSITIVE LOGITS
    çļĦéģĵçIJĨ
    0.09
    æĻºèĢħ
    0.09
    è°ļ
    0.08
    lighet
    0.08
    è°ļè¯Ń
    0.07
    éª
    0.07
    亦çĦ¶
    0.07
    åħ¨éĿ¢æ·±åĮĸæĶ¹éĿ©
    0.07
    lichen
    0.07
     proverb
    0.07
    Activations Density 0.008%

    No Known Activations