© 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. 8085
    Prev
    Next
    INDEX
    Explanations

    at the angle specified

    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
    æľ¬ç½ij
    -0.08
    eza
    -0.07
    lops
    -0.07
    æĿ¥çļĦæŶåĢĻ
    -0.07
    éĩįæĿ¥
    -0.07
    ä¸įæĢĿ
    -0.07
    áĥ¬áĥ§
    -0.07
    ÙĦز
    -0.07
    airo
    -0.06
    太ä¸Ĭ
    -0.06
    POSITIVE LOGITS
    æĮĩå®ļçļĦ
    0.08
    kuš
    0.07
    çī¹å®ļçļĦ
    0.07
    éļıæĦıçļĦ
    0.07
     specified
    0.07
    omal
    0.07
    ä»»æĦı
    0.07
     arbitrary
    0.07
    éļıæĦı
    0.07
    uzzi
    0.06
    Activations Density 0.244%

    No Known Activations