© 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. 15967
    Prev
    Next
    INDEX
    Explanations

    speed, speeding, slow

    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
    èĤ¥æ²ĥ
    -0.08
    çļĦæīĭæĮĩ
    -0.08
    ä¿ĺ
    -0.08
     Overflow
    -0.07
    æ²ŁæĿij
    -0.07
    aben
    -0.07
     luas
    -0.07
     Monat
    -0.07
    ç´¯çļĦ
    -0.07
    çļ±
    -0.07
    POSITIVE LOGITS
     speed
    0.14
     speeds
    0.14
    éĢŁåº¦
    0.14
    çļĦéĢŁåº¦
    0.12
    speed
    0.12
    _speed
    0.11
    Speed
    0.11
    -speed
    0.11
     ÑģкоÑĢоÑģÑĤÑĮ
    0.11
     tá»ijc
    0.11
    Activations Density 0.046%

    No Known Activations