© 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. 16904
    Prev
    Next
    INDEX
    Explanations

    comparing New York fruit fashion women

    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
     afterward
    -0.05
    åĩĨèĢĥè¯ģ
    -0.05
    åłĤçļĩ
    -0.05
    缴æİ¥æĪĸ
    -0.05
    ç«łç¨ĭ
    -0.05
    estone
    -0.05
     afterwards
    -0.05
    æ½Ľ
    -0.05
    rab
    -0.05
    reo
    -0.05
    POSITIVE LOGITS
    åĽ
    0.06
    fällig
    0.06
    h
    0.06
    “
    0.05
    toa
    0.05
    ponder
    0.05
    ä¸įåĩº
    0.05
     dermed
    0.05
    è°ĥ
    0.05
    aster
    0.05
    Activations Density 0.297%

    No Known Activations