© 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. 19801
    Prev
    Next
    INDEX
    Explanations

    revised proposal

    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
    und
    -0.07
    å®ħ
    -0.06
    ia
    -0.06
    antz
    -0.06
    bb
    -0.06
    etz
    -0.06
    ogan
    -0.06
    bbc
    -0.06
     sharply
    -0.06
    ishes
    -0.06
    POSITIVE LOGITS
    kos
    0.08
    metis
    0.08
    ãģĬãģĭ
    0.07
    æľ¬çıŃ
    0.07
    uhn
    0.07
    'L
    0.07
     racked
    0.07
    代夫
    0.07
    mettere
    0.07
    .Pow
    0.07
    Activations Density 0.003%

    No Known Activations