© 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. 63899
    Prev
    Next
    INDEX
    Explanations

    mathematical or code structures

    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
    luž
    -0.07
    atis
    -0.07
    .partition
    -0.06
     Ers
    -0.06
    urts
    -0.06
     lãnh
    -0.06
    æĺ¯ä¼ļ
    -0.06
     buflen
    -0.06
    æĸ°éĶIJ
    -0.06
    ä¸į好äºĨ
    -0.06
    POSITIVE LOGITS
    å¤į
    0.07
    -private
    0.07
    _gate
    0.07
    .expect
    0.07
    hana
    0.07
    halle
    0.06
    çĶŁåij½è´¢äº§å®īåħ¨
    0.06
    ancell
    0.06
     Mills
    0.06
    ç§ģ
    0.06
    Activations Density 0.001%

    No Known Activations