© 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. 9416
    Prev
    Next
    INDEX
    Explanations

    variable assignment or declaration

    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
    ZER
    -0.06
    é¢ĺ
    -0.06
    åħĦå¼Ł
    -0.06
    libs
    -0.06
    pliers
    -0.06
    è§Ħç«ł
    -0.06
    碧
    -0.06
     tÃŃ
    -0.06
    tev
    -0.06
    ly
    -0.05
    POSITIVE LOGITS
    ##_
    0.09
    OMIC
    0.08
    anut
    0.08
    è·Łèĩªå·±
    0.07
    Ïīμα
    0.07
    ifter
    0.07
    etre
    0.07
    éf
    0.07
    [...,
    0.07
    ìĺ¤ëĭĪ
    0.07
    Activations Density 0.009%

    No Known Activations