© 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. 13092
    Prev
    Next
    INDEX
    Explanations

    departments and teams

    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
    åħ¬éģĵ
    -0.08
    çĶ±æĶ¿åºľ
    -0.07
    éŀłèº¬
    -0.07
    æľ¬äººåľ¨
    -0.07
    ä¸ŃåĽ½æĶ¿åºľ
    -0.07
    @student
    -0.07
     eer
    -0.07
    èѦæĸ¹
    -0.07
    è¯¥åĽ½
    -0.06
    åħ¬åı¸èij£äºĭéķ¿
    -0.06
    POSITIVE LOGITS
    çŃīéĥ¨éŨ
    0.11
    è´Łè´£å¯¹
    0.10
    è´Łè´£
    0.10
    主è¦ģè´Łè´£
    0.09
    åIJĦéĥ¨éŨ
    0.09
    éĥ¨éŨ
    0.08
     departments
    0.08
    è²łè²¬
    0.08
    éĥ¨éŨçļĦ
    0.08
    认é¢Ĩ
    0.08
    Activations Density 0.130%

    No Known Activations