© 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. 40003
    Prev
    Next
    INDEX
    Explanations

    drug addiction and abuse

    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
    çijķ
    -0.08
    aiss
    -0.08
    ÙĪÙĪ
    -0.08
    åħ°è¾¾
    -0.08
    æ´Ĵæ°´
    -0.07
    allax
    -0.07
    FAULT
    -0.07
    æĪijè¦ģæĬķè¯ī
    -0.07
    MOTE
    -0.07
    æ¹¿åľ°åħ¬åĽŃ
    -0.07
    POSITIVE LOGITS
    æĪIJçĺ¾
    0.15
    æ¯Ĵåĵģ
    0.14
    çĺ¾
    0.13
     addiction
    0.12
     heroin
    0.12
    åIJ¸æ¯Ĵ
    0.12
     addictive
    0.11
     marijuana
    0.11
    ä¸Ĭçĺ¾
    0.11
     cocaine
    0.11
    Activations Density 0.226%

    No Known Activations