© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 16864
    Prev
    Next
    INDEX
    Explanations

    side effects and toxicity

    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
     desesper
    -0.08
    engang
    -0.08
    çħ©æĥ±
    -0.07
    éĤªéŃĶ
    -0.07
    ÙĪرش
    -0.07
    orial
    -0.07
    å¼±çĶµ
    -0.07
    รว
    -0.07
    æĥij
    -0.07
     predic
    -0.07
    POSITIVE LOGITS
    åī¯ä½ľçĶ¨
    0.13
     побоÑĩнÑĭÑħ
    0.11
     побоÑĩ
    0.11
     Side
    0.10
     side
    0.09
     ë¶Ģìŀijìļ©
    0.09
    Side
    0.09
    åī¯
    0.08
    åľ¨ä½¿çĶ¨è¿ĩç¨ĭä¸Ń
    0.08
    side
    0.08
    Activations Density 0.230%

    No Known Activations