© 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. 1321
    Prev
    Next
    INDEX
    Explanations

    game elements

    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
    åIJĪãģĦ
    -0.07
    BlockSize
    -0.06
    ipi
    -0.06
     successive
    -0.06
     nep
    -0.06
     dipping
    -0.06
    Âł
    -0.06
    ãģ«åĩºãģ¦
    -0.06
    æݨä»ĭ
    -0.06
    æµģ转
    -0.06
    POSITIVE LOGITS
     density
    0.09
    _density
    0.08
    aranya
    0.08
    ész
    0.08
    å¯Ĩ度
    0.08
    ophage
    0.08
    arang
    0.08
     occupying
    0.08
    essor
    0.07
    Moved
    0.07
    Activations Density 0.012%

    No Known Activations