© 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. 22630
    Prev
    Next
    INDEX
    Explanations

    numbers between 0 and 1

    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
    kens
    -0.06
    диÑģ
    -0.05
    éĻIJ度
    -0.05
    оÑĤе
    -0.05
    ä¸Ģ度
    -0.05
    ائÙĬ
    -0.05
    -produ
    -0.05
     Karn
    -0.05
    é
    -0.05
     неÑĢа
    -0.05
    POSITIVE LOGITS
    ipy
    0.07
    éĢī人
    0.06
    sey
    0.06
    ior
    0.05
    ips
    0.05
    rée
    0.05
    anol
    0.05
    hä
    0.05
    uy
    0.05
    rán
    0.05
    Activations Density 0.007%

    No Known Activations