© 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. 4591
    Prev
    Next
    INDEX
    Explanations

    problems and difficulties

    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
     cautiously
    -0.07
    èĢIJ
    -0.07
    ç»ĵåIJĪèµ·æĿ¥
    -0.06
    .flags
    -0.06
    awa
    -0.06
     plutôt
    -0.06
    orc
    -0.06
    æĽ´åħ¨éĿ¢
    -0.06
    èĩ³å°ijåľ¨
    -0.06
     piuttosto
    -0.06
    POSITIVE LOGITS
    æĢİä¹ĪåĬŀåij¢
    0.09
     unwanted
    0.09
     âĵĺ
    0.07
    inton
    0.07
     threaten
    0.07
    urg
    0.07
    容æĺĵéĢłæĪIJ
    0.07
    ãģĹãģĮ
    0.07
    容æĺĵ产çĶŁ
    0.07
    å¨ģèĥģ
    0.07
    Activations Density 0.608%

    No Known Activations