© 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. 22531
    Prev
    Next
    INDEX
    Explanations

    toxicity and hazard assessment

    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
     aps
    -0.07
    管çIJĨæĿ¡ä¾ĭ
    -0.07
    è¡ĵ
    -0.07
    æľīæĿĥä¿ĿçķĻ
    -0.07
    Ñħом
    -0.07
    è¦ıç´Ħ
    -0.07
     religios
    -0.07
    ιδ
    -0.07
     Zuk
    -0.07
    enta
    -0.07
    POSITIVE LOGITS
    éĻIJåĢ¼
    0.09
     lifecycle
    0.09
    æ¯Ĵ
    0.08
    åĮĸåѦåĵģ
    0.08
     toxicity
    0.08
    åģ¥åº·å®īåħ¨
    0.08
     Hazard
    0.08
     dose
    0.08
     extrapol
    0.08
     hazard
    0.08
    Activations Density 0.056%

    No Known Activations