© 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. 50194
    Prev
    Next
    INDEX
    Explanations

    derivative

    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
    abella
    -0.07
    ola
    -0.07
    รู
    -0.07
    hiba
    -0.07
    çļĦ人工æĻºèĥ½
    -0.07
    (MSG
    -0.07
    ł
    -0.06
    è¯
    -0.06
    upt
    -0.06
    /cms
    -0.06
    POSITIVE LOGITS
     Shea
    0.07
    estra
    0.07
    åħ¶å®ĥçļĦ
    0.06
    以åıĬ对
    0.06
    è¿ĻäºĽéĥ½æĺ¯
    0.06
    äch
    0.06
    è¿ĻäºĽéĥ½
    0.06
    åı¦å¤ĸè¿ĺæľī
    0.06
    以åıĬåIJĦç§į
    0.06
    ther
    0.06
    Activations Density 0.043%

    No Known Activations