© 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. 27351
    Prev
    Next
    INDEX
    Explanations

    technical requests and updates

    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
    ometown
    -0.08
    itunes
    -0.08
    æĺ¯ä¸įæĺ¯å¾Ī
    -0.08
    çĴŀ
    -0.08
    ervlet
    -0.08
    åįĥä¸ĩä¸įèĥ½
    -0.07
    mploy
    -0.07
     punc
    -0.07
    راÙģ
    -0.07
    orex
    -0.07
    POSITIVE LOGITS
    æĸ°åĬŁèĥ½
    0.08
     TODO
    0.07
     workaround
    0.07
     developers
    0.07
     migration
    0.07
     implementations
    0.07
     currently
    0.07
     github
    0.07
     GitHub
    0.07
     existing
    0.07
    Activations Density 1.208%

    No Known Activations