© 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. 8978
    Prev
    Next
    INDEX
    Explanations

    function and variable names

    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
    大家éĥ½çŁ¥éģĵ
    -0.07
    ston
    -0.07
    acr
    -0.06
    åįł
    -0.06
    fmt
    -0.06
    çĦ¶å¤§
    -0.06
    -r
    -0.06
    åħ·å¤ĩä¸Ģå®ļçļĦ
    -0.06
    forth
    -0.06
    ÚĨÙĩ
    -0.06
    POSITIVE LOGITS
    _NONNULL
    0.08
    èħ¹
    0.08
    ä¹°ä¹°
    0.08
    ,proto
    0.08
    å¾Ĵ
    0.07
    oteca
    0.07
    Reusable
    0.07
    _ABI
    0.07
     мили
    0.07
    ilename
    0.07
    Activations Density 0.008%

    No Known Activations