© 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. 61815
    Prev
    Next
    INDEX
    Explanations

    zero or off

    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
    bilt
    -0.08
    å¨ģ
    -0.07
    ixa
    -0.07
    ÙĬÙģÙĬØ©
    -0.07
     Ingr
    -0.07
    æŃ
    -0.07
    semb
    -0.07
    æī¿æİ¥
    -0.07
    iller
    -0.07
    hte
    -0.07
    POSITIVE LOGITS
    éĢ¼
    0.08
    éĻ¤éĿŀ
    0.08
     unless
    0.08
     except
    0.07
    è¿Ľä¸ĢæŃ¥å¢ŀ强
    0.07
    [:]
    0.07
     âĪĢ
    0.07
    åİ»è¿ĩ
    0.07
    çķĻ
    0.07
    为佳
    0.07
    Activations Density 0.002%

    No Known Activations