© 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. 17956
    Prev
    Next
    INDEX
    Explanations

    HTML entities

    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
    åIJijå¤ĸ
    -0.06
     veille
    -0.05
    ãĥ¯ãĥ¼
    -0.05
    ä¸įä½ıçļĦ
    -0.05
    .Call
    -0.05
     postan
    -0.05
    社ä¼ļåĽ¢ä½ĵ
    -0.05
    ä¸Ģå®ļç¨ĭ度
    -0.05
    ç¬ĭ
    -0.05
    ensif
    -0.05
    POSITIVE LOGITS
    lav
    0.06
    inz
    0.06
    Lav
    0.06
    inch
    0.06
    borne
    0.05
     Lav
    0.05
    ruta
    0.05
    ç©¿è¶Ĭ
    0.05
    arde
    0.05
     passaggi
    0.05
    Activations Density 0.011%

    No Known Activations