© 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. 21003
    Prev
    Next
    INDEX
    Explanations

    foreign characters

    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
    -0.07
    lu
    -0.06
    à¸ĸ
    -0.06
    ected
    -0.05
    æĪĸåĪłéĻ¤
    -0.05
    çļĦåIJĮåѦ
    -0.05
    æī§
    -0.05
    влÑıеÑĤÑģÑı
    -0.05
    ut
    -0.05
    åľ¨æĢĿæĥ³ä¸Ĭ
    -0.05
    POSITIVE LOGITS
    ritch
    0.06
    izard
    0.06
    izer
    0.06
    åIJijåħ¶
    0.06
    Ñĩин
    0.06
    гон
    0.06
     considéra
    0.06
    hood
    0.06
    ай
    0.06
    YN
    0.06
    Activations Density 0.002%

    No Known Activations