© 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. 51560
    Prev
    Next
    INDEX
    Explanations

    at least

    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
     ie
    -0.07
    INLINE
    -0.07
    chie
    -0.07
    REET
    -0.06
    çĭ¬ç§Ģ
    -0.06
    æĽ´ä¸įèĥ½
    -0.06
    inie
    -0.06
    æĬ¤
    -0.06
     either
    -0.06
    è·¯åįĹ
    -0.06
    POSITIVE LOGITS
     jedenfalls
    0.10
    èĩ³å°ij
    0.10
     anyways
    0.09
    æĺ¯è¿Ļæł·
    0.09
    èĩ³å°ijåľ¨
    0.09
    èĩ³å°ijæľī
    0.08
    å°±æĺ¯è¿Ļä¹Ī
    0.08
     zumindest
    0.08
    sofar
    0.08
    icare
    0.08
    Activations Density 0.203%

    No Known Activations