© 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. 43944
    Prev
    Next
    INDEX
    Explanations

    but, have, can, then, such

    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
    ointed
    -0.08
    aped
    -0.07
    æĪĸ以åħ¶ä»ĸæĸ¹å¼ı
    -0.07
    å±ħå¤ļ
    -0.07
    awal
    -0.07
    éĢļè¿ĩåIJĦç§į
    -0.07
    Started
    -0.07
    ulas
    -0.07
    äºijä¸Ń
    -0.07
    ä¸ĢèĪ¬ä¸º
    -0.07
    POSITIVE LOGITS
    ãģªãĤĵãģ¨
    0.09
    æľīä¸Ģç§į
    0.08
    åħ³éĶ®åľ¨äºİ
    0.07
     actually
    0.07
    è¿ĺæľīä¸Ģç§į
    0.07
    !
    0.07
    å®Łãģ¯
    0.07
     justru
    0.07
    éĿŀ常ç®Ģåįķ
    0.07
     tzv
    0.07
    Activations Density 0.298%

    No Known Activations