© 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. 17022
    Prev
    Next
    INDEX
    Explanations

    dealing with challenges

    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
     ARTIC
    -0.06
    Disappear
    -0.06
    ä¸Ģç«Ļå¼ı
    -0.06
    asy
    -0.06
    çī¹åĪ«æĺ¯
    -0.06
    ä¸ĢäºĽå°ı
    -0.06
    kach
    -0.06
     eten
    -0.05
     дÑĢÑĥз
    -0.05
     terc
    -0.05
    POSITIVE LOGITS
    å¿įåıĹ
    0.05
    ilton
    0.05
     dozens
    0.05
    ÙĴ
    0.05
    ále
    0.05
    Ñĥже
    0.05
     countless
    0.05
    åIJĮæŶè¿ĺè¦ģ
    0.05
    éĿ¢å¯¹çļĦ
    0.05
     mime
    0.05
    Activations Density 0.044%

    No Known Activations