© 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. 52028
    Prev
    Next
    INDEX
    Explanations

    criminal damage and property 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
    è½½åħ¥
    -0.08
    ailing
    -0.08
    flow
    -0.07
    èĥĥéĥ¨
    -0.07
    _defs
    -0.07
    è´Ńåľ°
    -0.07
    éħ
    -0.07
    èĥĮéĿł
    -0.07
    eking
    -0.07
    éħĴåºĹé¢Ħ订
    -0.07
    POSITIVE LOGITS
    æįŁå¤±
    0.14
    æįŁåĿı
    0.13
    çļĦæįŁå¤±
    0.13
    æįŁèĢĹ
    0.13
    æįŁæ¯ģ
    0.13
    æįŁå¤±çļĦ
    0.12
     damage
    0.12
    ä¿Ŀ管
    0.12
    æIJį失
    0.11
     losses
    0.11
    Activations Density 0.047%

    No Known Activations