© 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. 23502
    Prev
    Next
    INDEX
    Explanations

    -di velocity

    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
    ESTA
    -0.08
    che
    -0.07
    ÙĥÙĬ
    -0.06
    éĿ
    -0.06
    رة
    -0.06
    ÙĬرة
    -0.06
    è¿ĻåĽĽ
    -0.06
    èĢģå®ŀ
    -0.06
    æŃ¢çĹĽ
    -0.06
    ãĤ±
    -0.06
    POSITIVE LOGITS
    untu
    0.08
    onta
    0.08
    tui
    0.08
     eff
    0.07
    å·§å¦Ļ
    0.07
    æ¡£
    0.07
    ÑįÑĦ
    0.07
    åIJĪä½ľçĶ¨
    0.07
    allo
    0.07
    æ²¼
    0.07
    Activations Density 0.002%

    No Known Activations