© 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. 13588
    Prev
    Next
    INDEX
    Explanations

    biological traits

    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
    astas
    -0.07
    asley
    -0.07
    thon
    -0.07
    å¾Ĵ
    -0.07
    дили
    -0.07
    hlen
    -0.07
    sid
    -0.07
    çļĦæĥħå½¢
    -0.07
     proceedings
    -0.07
    LY
    -0.07
    POSITIVE LOGITS
     traits
    0.11
    æĢ§çĬ¶
    0.09
    Traits
    0.09
     trait
    0.09
     Traits
    0.09
    trait
    0.09
    éģĹä¼ł
    0.08
    traits
    0.08
     Trait
    0.08
    åIJİ天
    0.08
    Activations Density 0.073%

    No Known Activations