© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 41351
    Prev
    Next
    INDEX
    Explanations

    felony, misdemeanor, crime, offence

    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
    Not in Any Lists

    No Comments

    Negative Logits
    Tween
    -0.07
    angel
    -0.07
    laces
    -0.07
    èĦī
    -0.07
    æĴij
    -0.07
     healthier
    -0.07
     Sehat
    -0.07
    åĩłåıª
    -0.07
     Cuma
    -0.06
    rowsing
    -0.06
    POSITIVE LOGITS
     punishable
    0.12
     crimes
    0.11
     offenses
    0.10
     felony
    0.09
     crime
    0.09
     offences
    0.09
     деÑı
    0.09
    çĬ¯ç½ªè¡Į为
    0.09
     пÑĢеÑģÑĤÑĥплениÑı
    0.09
     Crimes
    0.08
    Activations Density 0.119%

    No Known Activations