© 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. 22047
    Prev
    Next
    INDEX
    Explanations

    becomes or equals

    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
    项è§Ħå®ļ
    -0.06
    ноÑģ
    -0.06
    æĬ¥åijĬæĺ¾ç¤º
    -0.06
     induk
    -0.06
     artis
    -0.06
    æĩ
    -0.05
    oweit
    -0.05
    iosk
    -0.05
    wyn
    -0.05
     prolet
    -0.05
    POSITIVE LOGITS
    alami
    0.07
    éĩı
    0.06
    为å¸Ī
    0.05
    [opt
    0.05
    bankan
    0.05
    clés
    0.05
    æĶ¯
    0.05
    æĭ¾
    0.05
    Ãłng
    0.05
    ä¸įè°ĥ
    0.05
    Activations Density 0.011%

    No Known Activations