© 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. 21132
    Prev
    Next
    INDEX
    Explanations

    image operations

    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
    æľīæѤ
    -0.06
    kuat
    -0.05
    è¿Ļ个åIJįåŃĹ
    -0.05
     shut
    -0.05
     weak
    -0.05
     tailor
    -0.05
    æĪIJç«ł
    -0.05
    ept
    -0.05
    åĨį说
    -0.05
    หาà¸ĩ
    -0.05
    POSITIVE LOGITS
    ersen
    0.07
     Helm
    0.06
    oge
    0.06
    åģļæ³ķ
    0.05
    rama
    0.05
    okol
    0.05
    деб
    0.05
    à·IJ
    0.05
    ç¥Ľ
    0.05
    æĭ¼
    0.05
    Activations Density 0.003%

    No Known Activations