© 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. 21584
    Prev
    Next
    INDEX
    Explanations

    nifedipine, ropivacaine, bupivacaine

    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
    -0.06
    ä¹ĭä¸Ģå°±æĺ¯
    -0.05
    .
    -0.05
    æĮł
    -0.05
     gì
    -0.05
    è¡Įæĥħ
    -0.05
    ...
    -0.05
    [
    -0.05
    Camp
    -0.05
    emann
    -0.04
    POSITIVE LOGITS
    æĺ¯ä½łä»¬
    0.07
    ä½Ĩä¸įéĻIJäºİ
    0.07
    è°¢è°¢ä½łä»¬
    0.06
    ä¹ĭéķ¿
    0.06
    ä¸Ģå¼łå¼ł
    0.06
    vend
    0.06
    æĢ¨
    0.06
    =?,
    0.06
    ä¸īå®Ŀ
    0.06
    ustos
    0.06
    Activations Density 0.077%

    No Known Activations