© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 20279
    Prev
    Next
    INDEX
    Explanations

    oral administration or treatment

    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
    iard
    -0.07
    å¼ĤçļĦ
    -0.06
    astra
    -0.06
    uevo
    -0.06
    سبب
    -0.06
    erals
    -0.05
     Ú¯ÙĪÙĨÙĩ
    -0.05
    arrera
    -0.05
    گاÙĩ
    -0.05
    ç§į
    -0.05
    POSITIVE LOGITS
    icket
    0.06
    æ¯ĶæĭŁ
    0.06
    issé
    0.06
    amus
    0.06
    ä¸įåĬĽ
    0.06
    اØŃت
    0.06
    dat
    0.05
    à¹ĥหà¸įà¹Ī
    0.05
    大æĦı
    0.05
    goog
    0.05
    Activations Density 0.009%

    No Known Activations