© 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. 3794
    Prev
    Next
    INDEX
    Explanations

    mathematical operations or code components

    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
    -addons
    -0.09
    èī²åĪĹ
    -0.07
    ereum
    -0.07
    aimana
    -0.07
    ìł
    -0.07
    ÅĻád
    -0.07
    roup
    -0.06
    elpers
    -0.06
    erdade
    -0.06
     ÐŁÐ¾Ð¿ÑĢо
    -0.06
    POSITIVE LOGITS
    ahi
    0.07
     exclude
    0.07
    uft
    0.07
    ah
    0.07
    سÙĩ
    0.07
    am
    0.07
    ä¸įæĶ¹
    0.07
    omm
    0.06
    oh
    0.06
    é£ĺé£ĺ
    0.06
    Activations Density 0.023%

    No Known Activations