© 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. 22043
    Prev
    Next
    INDEX
    Explanations

    superlative positions

    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
    uit
    -0.09
    ×ķ׳×Ļ
    -0.09
    u
    -0.08
    ×ķ
    -0.08
    o
    -0.08
    ably
    -0.07
    ÏĤ
    -0.07
    outs
    -0.07
    ier
    -0.07
    -être
    -0.07
    POSITIVE LOGITS
    arki
    0.09
    å²ģçļĦåŃ©åŃIJ
    0.08
    ixer
    0.08
    áĥIJáĥª
    0.08
    liegende
    0.08
    sver
    0.07
    aybe
    0.07
    emento
    0.07
    ева
    0.07
    γά
    0.07
    Activations Density 0.008%

    No Known Activations