© 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. 61237
    Prev
    Next
    INDEX
    Explanations

    distribution, conjecture, steady-state, integral, corrected, reflex

    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
    udas
    -0.08
    uda
    -0.07
     Pud
    -0.07
    è¶Ł
    -0.07
    ãĤĵãģ³
    -0.07
    ãģ«ãģĤãģŁ
    -0.06
    çķ¥
    -0.06
    å¢ŀåĢ¼
    -0.06
    inga
    -0.06
    çĪ±æĥľ
    -0.06
    POSITIVE LOGITS
    éļıçĿĢ
    0.15
    ä½ĨéļıçĿĢ
    0.14
    è¶ĬæĿ¥è¶Ĭ
    0.13
    åıĺå¾Ĺè¶ĬæĿ¥è¶Ĭ
    0.13
    ä¼ļéļıçĿĢ
    0.12
    éļıçĿĢæŶéĹ´çļĦ
    0.12
    éļ¨èijĹ
    0.12
    æĦĪæĿ¥æĦĪ
    0.12
    èĢĮéļıçĿĢ
    0.12
    å§ĭç»Īä¿ĿæĮģ
    0.12
    Activations Density 0.124%

    No Known Activations