© 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. 21555
    Prev
    Next
    INDEX
    Explanations

    the day

    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
    wege
    -0.08
    åĩĢé¢Ŀ
    -0.06
    wegs
    -0.06
    ç«ł
    -0.06
    weg
    -0.06
    веÑĢÑĪенÑģÑĤво
    -0.06
    -prev
    -0.06
     Powered
    -0.06
    æĻ®éĢļåIJĪä¼Ļ
    -0.06
     forthcoming
    -0.06
    POSITIVE LOGITS
    ä¸Ģ寸
    0.06
    æ¯Ķåħ¶ä»ĸ
    0.05
    ified
    0.05
    åĪĨæŶ
    0.05
    {{
    0.05
    inf
    0.05
    коÑģÑĤÑĮ
    0.05
     toler
    0.05
    åĴĮæ°Ķ
    0.05
    è¯ģæĺİ
    0.05
    Activations Density 0.015%

    No Known Activations