© 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. 13625
    Prev
    Next
    INDEX
    Explanations

    importance, function, 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
    rippling
    -0.09
    ToFront
    -0.08
    usso
    -0.08
     PROFESS
    -0.08
    ipel
    -0.08
    vio
    -0.08
    lettere
    -0.07
    太éĥİ
    -0.07
    versa
    -0.07
    usercontent
    -0.07
    POSITIVE LOGITS
    åıĸåĨ³äºİ
    0.08
    æĢ»ç»ĵå¦Ĥä¸ĭ
    0.08
     depends
    0.08
    å¦Ĥä¸ĭ
    0.08
     varies
    0.08
    éĹ®é¢ĺæĺ¯
    0.08
    缮æłĩæĺ¯
    0.08
     заклÑİÑĩаеÑĤÑģÑı
    0.08
    ä¹ĭå¤Ħåľ¨äºİ
    0.08
    æĿ¡ä»¶æĺ¯
    0.08
    Activations Density 0.419%

    No Known Activations