© 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. 8062
    Prev
    Next
    INDEX
    Explanations

    square roots or mathematical expressions

    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
    noinspection
    -0.07
    it
    -0.06
    g
    -0.06
    ↵↵
    -0.06
    IJ
    -0.06
    ij
    -0.06
     weshalb
    -0.06
    -0.06
    ↵↵↵
    -0.06
     (
    -0.06
    POSITIVE LOGITS
    (Font
    0.08
    æ±Ĥæĺ¯
    0.08
    reten
    0.08
    бини
    0.08
    ä¸ĸ代
    0.08
    ategori
    0.08
    utherland
    0.07
     despla
    0.07
    åıĹåĪ°äºĨ
    0.07
    IMPLEMENT
    0.07
    Activations Density 0.017%

    No Known Activations