© 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. 19002
    Prev
    Next
    INDEX
    Explanations

    issues and justifications

    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
    benh
    -0.08
    óa
    -0.07
    éĤ£æĺ¯åĽłä¸º
    -0.06
    è´¾
    -0.06
    åıªä»£è¡¨
    -0.06
    ÚĺÙĩ
    -0.06
    æĤ¨è¿ĺåı¯ä»¥
    -0.06
    éħ
    -0.06
    appa
    -0.06
    åĬ¿åľ¨å¿ħ
    -0.06
    POSITIVE LOGITS
     presumably
    0.10
    -mf
    0.08
    --[
    0.07
    åľ¨ç»Ļ
    0.07
     //.
    0.07
     probably
    0.07
    arpa
    0.07
    umably
    0.07
    nodoc
    0.07
    orney
    0.07
    Activations Density 0.016%

    No Known Activations