© 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. 16667
    Prev
    Next
    INDEX
    Explanations

    dark noun

    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
    ity
    -0.08
    orgeous
    -0.07
    istrator
    -0.06
    yers
    -0.06
    ว
    -0.06
    mul
    -0.06
     Toolbox
    -0.06
    etje
    -0.06
    ÑİÑĤ
    -0.06
    æľīéĴĪ对æĢ§çļĦ
    -0.06
    POSITIVE LOGITS
    äºİä¸Ģ
    0.08
    erer
    0.07
    s
    0.06
    st
    0.06
     sparing
    0.06
     Gau
    0.05
    ivate
    0.05
    è¡Ģ
    0.05
    b
    0.05
    in
    0.05
    Activations Density 0.005%

    No Known Activations