© 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. 3739
    Prev
    Next
    INDEX
    Explanations

    idiom, them has, Coupe requires, programs work

    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
    è¿Ļæł·å°±åı¯ä»¥
    -0.07
    iseksi
    -0.06
    ilton
    -0.06
    åľ°éģĵ
    -0.06
    çº
    -0.06
    彤
    -0.06
    å°±è¡ĮäºĨ
    -0.06
     sebab
    -0.06
    è¿Ļæł·æīįèĥ½
    -0.06
    ames
    -0.06
    POSITIVE LOGITS
    èĻ½æĺ¯
    0.08
    èĻ½çĦ¶æĺ¯
    0.07
    uose
    0.07
    éĴ£
    0.07
     mó
    0.07
    egi
    0.07
    个æĢ§
    0.07
    icato
    0.07
    ardu
    0.07
    herits
    0.07
    Activations Density 0.374%

    No Known Activations