© 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. 21446
    Prev
    Next
    INDEX
    Explanations

    numbers and articles

    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
    éļ¾æ±Ĥ
    -0.07
    dür
    -0.06
    èģļåĬĽ
    -0.06
    ìĤ´
    -0.06
    our
    -0.06
    ipan
    -0.06
    åĬªåĬĽå®ŀçİ°
    -0.06
     proportion
    -0.06
    离线
    -0.06
    гоÑĢа
    -0.06
    POSITIVE LOGITS
    æľī趣
    0.06
    çĶŁ
    0.06
     mens
    0.06
    (es
    0.05
     Mens
    0.05
    积æŀģ
    0.05
    åįİ
    0.05
     pé
    0.05
    ys
    0.05
    Ñĭв
    0.05
    Activations Density 0.003%

    No Known Activations