© 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. 21592
    Prev
    Next
    INDEX
    Explanations

    how to proceed

    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
    ãĤĴç«ĭãģ¦
    -0.07
    ingles
    -0.06
    sel
    -0.06
     dispose
    -0.05
    äº¤æĽ¿
    -0.05
    ä¸ĩ次
    -0.05
     popular
    -0.05
    ownic
    -0.05
    æľį
    -0.05
    à¸Ĭ
    -0.05
    POSITIVE LOGITS
    è¿ĻäºĽæķ°æį®
    0.06
    áĥĿáĥĵ
    0.06
    è¿ĻäºĽä¿¡æģ¯
    0.05
    ä¿¡æģ¯çļĦ
    0.05
    æĺ¯äººä½ĵ
    0.05
    水份
    0.05
    ungkap
    0.05
    ãģĭãģķ
    0.05
    åįİåºľ
    0.05
    为好åıĭ
    0.05
    Activations Density 0.014%

    No Known Activations