© 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. 21264
    Prev
    Next
    INDEX
    Explanations

    time progression

    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
    usia
    -0.06
    æĹ©çŁ¥éģĵ
    -0.05
    spo
    -0.05
    kul
    -0.05
    kek
    -0.05
    аÑģÑĭ
    -0.05
    ãĤŃ
    -0.05
    åĪ°ä½İ
    -0.05
    ä¹Łç½¢
    -0.05
    pok
    -0.05
    POSITIVE LOGITS
    æĢĿ
    0.06
    åįģæĹ¥
    0.06
     subsequent
    0.06
    äºİ
    0.06
    è·Łè¸ª
    0.06
    áss
    0.06
    Resolution
    0.06
    ä¹ĸ
    0.05
     Resolution
    0.05
    éļı
    0.05
    Activations Density 0.166%

    No Known Activations