© 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. 16805
    Prev
    Next
    INDEX
    Explanations

    minified js/css files

    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
    leven
    -0.06
    åĻĮ
    -0.06
     اÙģت
    -0.06
    èµ´ç¾İ
    -0.05
    ilit
    -0.05
    羡
    -0.05
    -aff
    -0.05
    æĺ¥æļĸ
    -0.05
     frequent
    -0.05
     wym
    -0.05
    POSITIVE LOGITS
    imit
    0.06
    @",
    0.05
     Gord
    0.05
    çŃĭ
    0.05
    orum
    0.05
    åѤåįķ
    0.05
    çļĦå°±æĺ¯
    0.05
    _decode
    0.05
    ä½ij
    0.05
    _hierarchy
    0.05
    Activations Density 0.060%

    No Known Activations