© 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. 63901
    Prev
    Next
    INDEX
    Explanations

    optimization techniques

    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
    ož
    -0.08
    ØŃر
    -0.08
    åįĹé£İ
    -0.08
    èįŀ
    -0.08
    zec
    -0.07
    ä¸Ģäºĭ
    -0.07
    è¿ľæµģ
    -0.07
    èķİ
    -0.07
    æĹłèĻij
    -0.07
    nop
    -0.07
    POSITIVE LOGITS
    loyd
    0.08
     Idi
    0.07
     initialised
    0.07
    agin
    0.07
     invented
    0.07
    ç»´æĬ¤
    0.07
    âĦ¢
    0.07
    _MAXIMUM
    0.07
     applic
    0.06
    ®
    0.06
    Activations Density 0.041%

    No Known Activations