© 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. 22360
    Prev
    Next
    INDEX
    Explanations

    "other" usage patterns

    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
    елÑı
    -0.07
    iq
    -0.06
    stdarg
    -0.06
    èģª
    -0.05
     تØŃص
    -0.05
    lega
    -0.05
    Pattern
    -0.05
    nor
    -0.05
    为åķ¥
    -0.05
    ä»İå·¦
    -0.05
    POSITIVE LOGITS
    å±ĭ
    0.07
    éĩĩ
    0.06
    anky
    0.06
    azes
    0.06
    æİĴ
    0.05
     implantação
    0.05
    æİ©
    0.05
     Ness
    0.05
    æİĴçļĦ
    0.05
     khas
    0.05
    Activations Density 0.001%

    No Known Activations