© 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. 37440
    Prev
    Next
    INDEX
    Explanations

    units and conversions

    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
    atan
    -0.07
     Maid
    -0.06
    ...
    -0.06
    æĺ¯åŁºäºİ
    -0.06
     nons
    -0.06
    éľ
    -0.06
     ln
    -0.05
    æ±Łå±±
    -0.05
    î
    -0.05
    endam
    -0.05
    POSITIVE LOGITS
    _plural
    0.09
    æİĪæ¬Ĭ
    0.08
    åħĭåĬĽ
    0.08
    Specifier
    0.08
    çĶ¸çĶ¸
    0.08
        ↵    ↵    ↵    ↵
    0.08
    æĿİåħĭ
    0.08
    ãm
    0.08
    owed
    0.08
    quee
    0.08
    Activations Density 0.005%

    No Known Activations