© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 21431
    Prev
    Next
    INDEX
    Explanations

    various languages statistics

    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
    æ»´æ°´
    -0.06
     poslov
    -0.06
    ettle
    -0.05
    ayos
    -0.05
    구ìļĶ
    -0.05
    olgált
    -0.05
    umm
    -0.05
     Nett
    -0.05
    ocas
    -0.05
    евиÑĩ
    -0.05
    POSITIVE LOGITS
    并讲è¯Ŀ
    0.06
    aran
    0.06
    åİŁåĽłæĺ¯
    0.05
    sbin
    0.05
    ém
    0.05
    поÑĢ
    0.05
    åĢĴæĺ¯
    0.05
    avis
    0.05
    åľ¨ä¸ĭéĿ¢
    0.05
    âĢ¹
    0.05
    Activations Density 0.057%

    No Known Activations