© 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. 44436
    Prev
    Next
    INDEX
    Explanations

    residual or leftover amounts

    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
    онÑĤ
    -0.07
    å§Ĺ
    -0.07
    onav
    -0.07
    maxlength
    -0.07
     banh
    -0.07
    éĢĶ
    -0.07
    åĸľéĹ»ä¹IJ
    -0.07
     ÑĥÑħа
    -0.07
    _INTERRUPT
    -0.06
    adero
    -0.06
    POSITIVE LOGITS
    æ®ĭçķĻ
    0.15
    æ®ĭä½Ļ
    0.14
     lingering
    0.13
     residual
    0.13
    çķĻåľ¨
    0.13
     linger
    0.11
    æ®ĭ
    0.11
    ãģ«æ®ĭ
    0.11
     remnants
    0.11
     leftover
    0.11
    Activations Density 0.061%

    No Known Activations