© 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. 33553
    Prev
    Next
    INDEX
    Explanations

    combination or composite

    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
    为æĤ¨æݨèįIJ
    -0.08
    renom
    -0.08
    eki
    -0.08
    <c
    -0.07
    enza
    -0.07
    egl
    -0.07
    ndon
    -0.07
    ató
    -0.07
     [+]
    -0.07
    lon
    -0.07
    POSITIVE LOGITS
     composite
    0.08
     combination
    0.08
     Combination
    0.07
    ç»ĦåIJĪ
    0.07
    æķ´ä½ĵçļĦ
    0.07
     combinations
    0.07
    å¤įåIJĪ
    0.07
    oine
    0.07
     Composite
    0.07
     bombe
    0.07
    Activations Density 0.168%

    No Known Activations