© 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. 2092
    Prev
    Next
    INDEX
    Explanations

    shape, size, version, approval

    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
    举ä¸Ģåıįä¸ī
    -0.07
     jer
    -0.07
    spe
    -0.07
    éŀł
    -0.06
    ath
    -0.06
    eren
    -0.06
    erb
    -0.06
    (+
    -0.06
    追æĿĢ
    -0.06
    +%
    -0.06
    POSITIVE LOGITS
    usercontent
    0.09
    èĭ¦è¾£
    0.08
    综
    0.08
    Ngu
    0.07
    ä¸įåĪ°çļĦ
    0.07
    ÂŃtion
    0.07
    سÙĤ
    0.07
    antro
    0.07
    .det
    0.07
    è¿Ļæīįæĺ¯
    0.07
    Activations Density 0.005%

    No Known Activations