© 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. 59140
    Prev
    Next
    INDEX
    Explanations

    criminal use of firearm

    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
    ä¿¡æģ¯çŃī
    -0.07
    ä¸įä¼ļ产çĶŁ
    -0.06
     GNU
    -0.06
    bis
    -0.06
    å¤Ħ
    -0.06
    åįİéĺ³
    -0.06
    iams
    -0.06
    æĮĿ
    -0.06
    æıIJè¦ģ
    -0.06
    emony
    -0.06
    POSITIVE LOGITS
    ague
    0.09
    amburger
    0.08
    pike
    0.08
    opak
    0.07
     ÑĪлÑı
    0.07
    ìł¤
    0.07
    沫
    0.07
    ÑĪÑĭ
    0.07
    htar
    0.07
    [dir
    0.07
    Activations Density 0.258%

    No Known Activations