© 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. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 21374
    Prev
    Next
    INDEX
    Explanations

    kernel technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/qwen-3.5-saes/qwen-3.5-4b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    xon
    -0.09
    gangs
    -0.08
    ybers
    -0.08
    agné
    -0.08
    rooms
    -0.08
    suming
    -0.08
    houses
    -0.08
    estu
    -0.08
    werkt
    -0.08
    geries
    -0.08
    POSITIVE LOGITS
    a
    0.07
    ly
    0.06
    ãģ®
    0.05
    ìĹIJ
    0.05
    en
    0.05
    cc
    0.05
    _
    0.05
    ìĿĺ
    0.05
     -
    0.04
    1
    0.04
    Activations Density 0.003%

    No Known Activations