© 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. 31021
    Prev
    Next
    INDEX
    Explanations

    digestion and appetite

    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
    éļ§
    -0.08
    weep
    -0.07
     ÙħسÙĦÙħ
    -0.07
    Rnd
    -0.07
    æµģè¡Ģ
    -0.07
    è¿«
    -0.07
     rond
    -0.07
    æĴķ
    -0.07
    缺水
    -0.07
    çļ®ä¹¦
    -0.07
    POSITIVE LOGITS
    æ¶ĪåĮĸ
    0.10
    æ¶ĪåĮĸçļĦ
    0.10
    æ¶ĪåĮĸä¸įèī¯
    0.09
     digestion
    0.09
    æ¶ĪåĮĸåIJ¸æĶ¶
    0.08
     ferment
    0.08
    èĥĥ
    0.08
     digest
    0.08
    积
    0.08
    é£Łæ¬²
    0.08
    Activations Density 0.015%

    No Known Activations