© 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. 38411
    Prev
    Next
    INDEX
    Explanations

    criminal acts and styles

    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
    æĪĸ以åħ¶ä»ĸæĸ¹å¼ı
    -0.07
    schaften
    -0.07
    ãĤŃãĥĵ
    -0.07
    бÑĥдÑĮ
    -0.07
     سÙĪÙī
    -0.07
    èĢĮè¿ĻäºĽ
    -0.07
    ä»İ缮åīį
    -0.07
     Insomma
    -0.06
     Curtain
    -0.06
    ä¸īé«ĺ
    -0.06
    POSITIVE LOGITS
    åĽłä¸ºä»ĸ
    0.09
    åħ¼
    0.09
     sekaligus
    0.09
    åĽłä¸ºå¥¹
    0.09
     puisqu
    0.07
    åĽłä¸ºæĪij们
    0.07
    åĽłä¸ºå®ĥ
    0.07
     disguised
    0.07
    /or
    0.07
    åĽłä¸ºæĪij
    0.07
    Activations Density 0.030%

    No Known Activations