© 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. 51451
    Prev
    Next
    INDEX
    Explanations

    US Pat. No

    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
    ÄĻt
    -0.07
    仲
    -0.06
     goodies
    -0.06
    _ASYNC
    -0.06
    åĪ°æł¡
    -0.06
    krit
    -0.06
    ament
    -0.06
    ç¦ıå¾·
    -0.06
    -main
    -0.06
     Eben
    -0.06
    POSITIVE LOGITS
    ØŃاد
    0.07
    å¢ħ
    0.07
     behalf
    0.07
    sdale
    0.07
    缸åħ³éĹ®çŃĶ
    0.07
    çļĦ人è¿ĺ
    0.07
    ÙĦد
    0.07
    ÙĨدر
    0.07
    ä½łæľīä»Ģä¹Ī
    0.07
    èģĶç³»åľ°åĿĢ
    0.07
    Activations Density 0.010%

    No Known Activations