© 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. 21065
    Prev
    Next
    INDEX
    Explanations

    list item separators

    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
    новиÑĩ
    -0.07
    ÏģίεÏĤ
    -0.07
    еÑĢб
    -0.07
    Ñĥл
    -0.07
    irim
    -0.07
    eses
    -0.07
    itous
    -0.06
    ноÑģли
    -0.06
    esel
    -0.06
    velopp
    -0.06
    POSITIVE LOGITS
     |
    0.06
    st
    0.05
     on
    0.05
    åı£æ°´
    0.05
    ample
    0.04
    æĶ
    0.04
    ·
    0.04
    éªı
    0.04
    éĽª
    0.04
     not
    0.04
    Activations Density 0.083%

    No Known Activations