© 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. 50805
    Prev
    Next
    INDEX
    Explanations

    PhD student or candidate

    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
    upan
    -0.09
    upp
    -0.07
    awan
    -0.07
    ari
    -0.07
    retta
    -0.07
    upe
    -0.07
    æļĸæļĸçļĦ
    -0.07
    imson
    -0.07
    pac
    -0.07
    compatible
    -0.07
    POSITIVE LOGITS
    ystack
    0.08
    ÌĢ
    0.07
    çĮľä½łåĸľæ¬¢
    0.07
    imis
    0.07
    ROTO
    0.06
    apos
    0.06
    æľ¬æĸĩæĿ¥èĩª
    0.06
    линг
    0.06
    allas
    0.06
    [Math
    0.06
    Activations Density 0.002%

    No Known Activations