© 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. 17979
    Prev
    Next
    INDEX
    Explanations

    rather than

    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
    åĮħæĭ¬ä½Ĩä¸įéĻIJäºİ
    -0.06
    æľ¨æĸ¯
    -0.06
    cil
    -0.06
    åĪĨ许
    -0.06
    åĮħæĭ¬
    -0.06
     kilom
    -0.06
    izations
    -0.06
    ä¹Łå°±
    -0.05
     ëĮĢíķ´ìĦľ
    -0.05
    è¡ĵ
    -0.05
    POSITIVE LOGITS
    uyla
    0.06
    é»ijçĻ½
    0.05
    ç¨Ģ
    0.05
    umble
    0.05
    ç»´æĸ¯
    0.05
    ycop
    0.05
    ovalo
    0.05
    éĥ½åĴĮ
    0.05
    alow
    0.05
     h
    0.05
    Activations Density 0.029%

    No Known Activations