© 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. 16744
    Prev
    Next
    INDEX
    Explanations

    code construct returns

    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
    å§ĭ
    -0.06
    endom
    -0.06
    çļĦåIJĪæĪIJ
    -0.06
    åľ°ä¸Ĭ
    -0.05
    æ··
    -0.05
     Powers
    -0.05
    å¤ĩçĶ¨
    -0.05
    ä»ĭ
    -0.05
    ivs
    -0.05
    å®ļ
    -0.05
    POSITIVE LOGITS
    ähr
    0.06
    heimer
    0.06
    æĪĸåħ¶
    0.05
    aste
    0.05
    ½ij
    0.05
    ä¼ĺèī¯çļĦ
    0.05
    èĥľè¿ĩ
    0.05
    度ãģª
    0.05
    æľīæĿ¡
    0.05
    æĶ¶éĵ¶
    0.05
    Activations Density 0.014%

    No Known Activations