© 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. 17373
    Prev
    Next
    INDEX
    Explanations

    statement usage

    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
    çĦ¶å¤§
    -0.06
    大æ¦Ĥæĺ¯
    -0.05
    atin
    -0.05
     sond
    -0.05
    ublik
    -0.05
    æĥij
    -0.05
    大æ´ĭ
    -0.05
    arele
    -0.05
    ä¸Ģçķª
    -0.05
    çļĦæŶåĢĻåı¯ä»¥
    -0.05
    POSITIVE LOGITS
    orz
    0.06
    eah
    0.06
     cosy
    0.06
    åIJİ顾ä¹ĭ忧
    0.06
    integr
    0.05
    frist
    0.05
    hô
    0.05
    rin
    0.05
    年头
    0.05
    bout
    0.05
    Activations Density 0.001%

    No Known Activations