© 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. 46996
    Prev
    Next
    INDEX
    Explanations

    hexadecimal numbers and bit operations

    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
     dumps
    -0.07
    catch
    -0.07
    Catch
    -0.07
     catch
    -0.07
    .catch
    -0.07
     catching
    -0.07
    绣æĪĺéĥ¨
    -0.07
    æįķ
    -0.07
     Chronicle
    -0.07
     bund
    -0.07
    POSITIVE LOGITS
    _GF
    0.07
    ä»įåľ¨
    0.07
    å°ļåľ¨
    0.06
    inear
    0.06
     Asian
    0.06
    天éŨ
    0.06
    é»į
    0.06
    转贴
    0.06
    示èĮĥæĢ§
    0.06
    çŁ¥éģĵä½ł
    0.06
    Activations Density 0.014%

    No Known Activations