© 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. 40387
    Prev
    Next
    INDEX
    Explanations

    variable/type annotations

    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
    ately
    -0.09
    iac
    -0.07
    ä¸Ģèµ·åľ¨
    -0.07
    ä¸ĭæĿ¥
    -0.07
    ä¸Ģ个åı«
    -0.07
    istr
    -0.07
    —and
    -0.07
    åıĪåľ¨
    -0.07
    retta
    -0.06
    åģļçļĦå°±æĺ¯
    -0.06
    POSITIVE LOGITS
    aksi
    0.08
    _REQUIRE
    0.08
    å²ij
    0.07
     напÑĢ
    0.07
    ä¾ĭå¦Ĥ
    0.07
    à¸Ķà¹ĩà¸Ī
    0.07
    æľ¬ç½ijç«Ļ
    0.07
    æ³ŀ
    0.07
    wart
    0.07
     disf
    0.07
    Activations Density 0.006%

    No Known Activations