© 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. 46183
    Prev
    Next
    INDEX
    Explanations

    killings and homicides

    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
     ridic
    -0.08
    ãi
    -0.07
    æĭ¶
    -0.07
    èij«
    -0.07
    æ¯ĽçĹħ
    -0.07
    çªĺå¢ĥ
    -0.07
    Ñģова
    -0.07
     mastur
    -0.07
    æĬĹè¡¡
    -0.07
    oser
    -0.07
    POSITIVE LOGITS
     deaths
    0.13
     death
    0.13
    æŃ»äº¡çļĦ
    0.12
    æŃ»äº¡
    0.12
    æ®ī
    0.12
    è¡Ģèħ¥
    0.12
    death
    0.12
    è¡Ģæµģ
    0.11
    身亡
    0.11
     killing
    0.11
    Activations Density 0.315%

    No Known Activations