© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 22421
    Prev
    Next
    INDEX
    Explanations

    is correct

    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
    Negative Logits
    edia
    -0.07
    :numel
    -0.06
    иÑģи
    -0.06
    ëłĪ
    -0.06
     à®ļà¯Ĩயà¯įய
    -0.06
    deles
    -0.06
    aksikan
    -0.06
    æĸ¯é¡¿
    -0.06
    edere
    -0.05
    èĴ¼
    -0.05
    POSITIVE LOGITS
    á»Ńa
    0.06
    aget
    0.06
    å®ŀäºĭæ±Ĥæĺ¯
    0.05
    è°Īä¸įä¸Ĭ
    0.05
    iard
    0.05
    uw
    0.05
    ién
    0.05
    æª
    0.05
    ag
    0.05
    亡
    0.05
    Activations Density 0.005%

    No Known Activations