© 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. 4719
    Prev
    Next
    INDEX
    Explanations

    short and large distances

    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
    à¸Ĭีà¸ŀ
    -0.09
    ornado
    -0.08
    äºĭå®ŀè¯ģæĺİ
    -0.08
    ardino
    -0.08
    γη
    -0.08
    istel
    -0.07
     compro
    -0.07
    æľŁæ»¡åIJİ
    -0.07
    ä»Ĭå¤ľ
    -0.07
    FAULT
    -0.07
    POSITIVE LOGITS
    éĻĦè¿ij
    0.07
    ä¸įæĪIJ
    0.07
    orable
    0.07
     (<
    0.07
    åĮºåŁŁ
    0.06
    saus
    0.06
    çªĸ
    0.06
    ä¸įåıij
    0.06
     region
    0.06
     behavior
    0.06
    Activations Density 0.005%

    No Known Activations