© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 30858
    Prev
    Next
    INDEX
    Explanations

    slow, fast, performance, compared

    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
    åĭ¤æģ³
    -0.08
    太å¤ļ
    -0.07
    .launch
    -0.07
    åĪ°æľŁ
    -0.07
    ìĿ´ëĿ¼ë©´
    -0.07
    huri
    -0.07
    yait
    -0.07
    åį³åĪ°
    -0.07
    olie
    -0.07
    .Throw
    -0.07
    POSITIVE LOGITS
     compared
    0.12
     Compared
    0.10
     generally
    0.10
    缸è¾ĥäºİ
    0.10
     Generally
    0.10
    缸æ¯Ķ
    0.09
    åĽłä¸ºæľī
    0.09
    ä¸ĢèĪ¬èĢĮè¨Ģ
    0.09
     due
    0.09
    缸æ¯Ķè¾ĥ
    0.09
    Activations Density 0.072%

    No Known Activations