© 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. 47198
    Prev
    Next
    INDEX
    Explanations

    sperm motility and chromatin

    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
    esak
    -0.10
    edral
    -0.09
    ä¹ĭæĢ¥
    -0.08
    ếm
    -0.08
    vrier
    -0.08
     jeito
    -0.08
    è¿Ŀæ³ķåĴĮä¸įèī¯ä¿¡æģ¯ä¸¾æĬ¥
    -0.08
    abouts
    -0.08
    NESS
    -0.08
    elpers
    -0.08
    POSITIVE LOGITS
    çĸ²åĬĽ
    0.10
    ç»Ŀ伦
    0.09
    acies
    0.09
    ×ķ×ķת
    0.07
    noinspection
    0.07
    nya
    0.07
    го
    0.07
    uous
    0.07
    人èĦī
    0.07
    ยà¹īำ
    0.07
    Activations Density 0.006%

    No Known Activations