© 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. 37546
    Prev
    Next
    INDEX
    Explanations

    missing energy or loss

    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
    боÑİ
    -0.07
    çģ¿
    -0.07
    onse
    -0.07
    ordio
    -0.07
    imson
    -0.07
    acam
    -0.07
    çľĭæ¸ħæ¥ļ
    -0.07
    kog
    -0.06
    .pe
    -0.06
    plib
    -0.06
    POSITIVE LOGITS
    éĢĥéĢ¸
    0.09
    åİ»åIJij
    0.09
    _ESCAPE
    0.08
    踪
    0.08
    失åİ»
    0.08
    .Escape
    0.08
     escapes
    0.08
     escaping
    0.08
     loss
    0.08
    eres
    0.08
    Activations Density 0.003%

    No Known Activations