© 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. 17072
    Prev
    Next
    INDEX
    Explanations

    Bronx

    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
     ens
    -0.05
     hence
    -0.05
     thus
    -0.05
     conf
    -0.05
    fern
    -0.05
     inf
    -0.05
     /
    -0.05
     “
    -0.05
    lets
    -0.05
    åĽłæѤèĢĮ
    -0.05
    POSITIVE LOGITS
    áĢŁ
    0.07
    heden
    0.06
    å°ıæĿ¿
    0.06
    paged
    0.06
    жек
    0.06
    umbo
    0.06
    iin
    0.06
    IST
    0.06
    мок
    0.06
     bamb
    0.06
    Activations Density 0.077%

    No Known Activations