© 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. 22366
    Prev
    Next
    INDEX
    Explanations

    in or was

    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
    åIJĪåIJĮæŶ
    -0.06
    åĢĴ
    -0.05
    ynchronously
    -0.05
    EAN
    -0.05
    ãģ«åıĸãĤĬ
    -0.05
    纬
    -0.05
    celer
    -0.05
    dei
    -0.05
    /context
    -0.05
    lep
    -0.05
    POSITIVE LOGITS
     Pra
    0.06
    åĪ«
    0.06
    esar
    0.05
    ä¸Ń大
    0.05
    ä¿ĿçķĻ
    0.05
    巨大
    0.05
    æĵģ
    0.05
    itif
    0.05
     Raw
    0.05
    èĩ³ä¸Ĭ
    0.05
    Activations Density 0.040%

    No Known Activations