© 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. 12575
    Prev
    Next
    INDEX
    Explanations

    police and departments

    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
    éĺģ
    -0.07
    äºıæįŁ
    -0.07
     sail
    -0.06
    ç»Ŀåľ°
    -0.06
    anager
    -0.06
    è¯Ħå§Ķ
    -0.06
     Pavilion
    -0.06
     fret
    -0.06
     defiant
    -0.06
    æĢªåħ½
    -0.06
    POSITIVE LOGITS
    æ²»å®ī
    0.11
    åĬŀæ¡Ī
    0.10
    çł´æ¡Ī
    0.10
    æī§æ³ķ
    0.10
    æĬ¥æ¡Ī
    0.10
     Kriminal
    0.10
    åıĸè¯ģ
    0.10
    ä¾¦çł´
    0.10
    è¾ĸåĮº
    0.10
    æĬĵèİ·
    0.10
    Activations Density 0.405%

    No Known Activations