© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 55063
    Prev
    Next
    INDEX
    Explanations

    graft watchdog

    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
    Negative Logits
     exhaust
    -0.09
    erein
    -0.08
    pers
    -0.08
     Exhaust
    -0.08
    çŁ¥ä¹İ
    -0.08
    haust
    -0.08
    .dom
    -0.07
     investigation
    -0.07
    ç¦ıåĪ©
    -0.07
     kiá»ĩt
    -0.07
    POSITIVE LOGITS
    komst
    0.08
    ItemType
    0.07
    êng
    0.06
    éĺµ
    0.06
    าะ
    0.06
    æĸĹ
    0.06
     berm
    0.06
    æĿİåŃIJ
    0.06
    atype
    0.06
    å¹³è¡Į
    0.06
    Activations Density 0.001%

    No Known Activations