© 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. 2712
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols

    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
    éĽ
    -0.07
    outine
    -0.06
    ces
    -0.06
    rax
    -0.06
    ub
    -0.06
    ivery
    -0.06
     اÙĦعÙĦ
    -0.06
    afka
    -0.06
    第ä¸īæŃ¥
    -0.06
    -it
    -0.06
    POSITIVE LOGITS
    ezi
    0.08
    .mix
    0.08
    weise
    0.07
    imine
    0.07
    ori
    0.07
    æİĴçļĦ
    0.07
    æ··
    0.07
    quam
    0.07
    elar
    0.07
    æĸŃ
    0.07
    Activations Density 0.096%

    No Known Activations