© 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. 3491
    Prev
    Next
    INDEX
    Explanations

    charged with crime or trial

    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
    éĢĢä¿Ŀ
    -0.06
    åħij
    -0.06
    Statistic
    -0.06
    èĩªåıij
    -0.06
    ç²Ĵ
    -0.05
    åįĴ
    -0.05
    _checker
    -0.05
    è¿Ŀæ³ķåĴĮä¸įèī¯
    -0.05
    èĩªåĪ¶
    -0.05
    çĮĽçĦ¶
    -0.05
    POSITIVE LOGITS
     charges
    0.11
     обвинениÑı
    0.10
    罪åIJį
    0.10
     wegen
    0.10
     Charges
    0.10
     convictions
    0.09
     proceedings
    0.09
    charges
    0.09
     обвин
    0.09
    æĮĩæݧ
    0.09
    Activations Density 1.052%

    No Known Activations