© 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. 43683
    Prev
    Next
    INDEX
    Explanations

    quantities of drugs, death, or injuries

    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
    veen
    -0.10
    æĬ½æŁ¥æ£ĢæŁ¥
    -0.09
     )))
    -0.09
    öp
    -0.09
    .mo
    -0.09
    arent
    -0.09
    kün
    -0.08
    颱
    -0.08
    adah
    -0.08
    çĸijä¼¼è¿Ŀè§Ħ
    -0.08
    POSITIVE LOGITS
    ↵
    0.07
     damage
    0.07
    è¾¾åĪ°
    0.06
     either
    0.06
     criteria
    0.06
    éĩį大
    0.06
    ç»ıæµİæįŁå¤±
    0.06
     classified
    0.06
    è¾¾åĪ°äºĨ
    0.06
     classification
    0.06
    Activations Density 0.003%

    No Known Activations