© 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. 16509
    Prev
    Next
    INDEX
    Explanations

    medical terminology or suffixes

    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
    ä¸īåĮº
    -0.09
    arate
    -0.07
    ikos
    -0.07
    erc
    -0.07
     sla
    -0.06
    è·¨
    -0.06
    ipv
    -0.06
    ersp
    -0.06
    ä¸īåľ°
    -0.06
    ä¸įä¸Ĭ
    -0.06
    POSITIVE LOGITS
    å°±æĺ¯çĶ¨
    0.08
    åį³ä»¥
    0.08
    .pick
    0.08
     ((__
    0.08
    éģ¸çĶ¨
    0.08
    éĢīæĭ©ä¸įåIJĮçļĦ
    0.07
    heber
    0.07
    خط
    0.07
    éĥ½æĺ¯çĶ¨
    0.07
    nock
    0.07
    Activations Density 0.546%

    No Known Activations