© 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. 41562
    Prev
    Next
    INDEX
    Explanations

    mathematical structures and expansions

    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
    inance
    -0.07
    åĪ«ç¦»
    -0.07
    ยม
    -0.07
    æĽ¿
    -0.07
    å¤į
    -0.07
    Fcn
    -0.07
     dÃłnh
    -0.07
    enj
    -0.07
    ãĥ¬ãĥĥãĥĪ
    -0.07
    apos
    -0.07
    POSITIVE LOGITS
    iley
    0.07
    ystems
    0.07
    å¯Ĩ
    0.07
    ucha
    0.06
     core
    0.06
    客ä½ĵ
    0.06
    iertos
    0.06
    core
    0.06
    缼
    0.06
    OnError
    0.06
    Activations Density 0.022%

    No Known Activations