© 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. 30926
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions or time calculation

    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
    ightly
    -0.08
    .googleapis
    -0.08
    ighted
    -0.08
    æĶ¶äºĨ
    -0.08
    ä¸įåłª
    -0.08
    ĥĿ
    -0.08
    sville
    -0.08
    鬣
    -0.08
    aeda
    -0.08
     sublicense
    -0.08
    POSITIVE LOGITS
    年代åĪĿ
    0.07
     otherwise
    0.07
    +n
    0.07
    空
    0.06
    xffffffff
    0.06
     Countdown
    0.06
     junk
    0.06
    éĹĬ
    0.06
     gradi
    0.06
    /null
    0.06
    Activations Density 0.011%

    No Known Activations