© 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. 20633
    Prev
    Next
    INDEX
    Explanations

    starting sequence or number

    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
    ä»İæĶ¿
    -0.07
    交éĢļèŃ¦å¯Ł
    -0.07
    ç¾Ĭ
    -0.07
     opdracht
    -0.07
     milli
    -0.07
    人æ°ijèŃ¦å¯Ł
    -0.07
    ìĺ
    -0.06
    dba
    -0.06
    ansk
    -0.06
    æĵį
    -0.06
    POSITIVE LOGITS
     shifted
    0.10
    shift
    0.08
     shifting
    0.08
     shifts
    0.08
    æ»ļåĬ¨
    0.08
    -shift
    0.08
     shift
    0.08
     Shift
    0.07
    移ä½į
    0.07
    Shift
    0.07
    Activations Density 0.002%

    No Known Activations