© 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. 19289
    Prev
    Next
    INDEX
    Explanations

    contact form

    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
    åı£å¤´
    -0.05
    æĮ¥
    -0.05
    æĶ¯
    -0.05
    ä¾Ŀ
    -0.05
    ç»´æĮģ
    -0.05
    bish
    -0.05
    -0.05
    æİ¨è¿Ľä¼ļ
    -0.05
     Provision
    -0.05
    ÑıÑĤи
    -0.05
    POSITIVE LOGITS
    å¤§ä½ľ
    0.07
    estin
    0.07
    kun
    0.06
    oil
    0.06
    å°ı家ä¼Ļ
    0.06
    ä¸įåıij
    0.06
    nano
    0.06
    鼶éĥ¨ä»¶
    0.06
    à¸Īิ
    0.06
    ELLO
    0.06
    Activations Density 0.026%

    No Known Activations