© 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. 20578
    Prev
    Next
    INDEX
    Explanations

    my after punctuation

    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
    ÑģÑĤеÑģÑĤвенно
    -0.07
     Trident
    -0.06
    æľªå°½
    -0.06
    çļĦçĶ¨
    -0.06
    wykle
    -0.06
    ç§ijéĻ¢
    -0.06
    ä¸įæĺİçļĦ
    -0.05
    ä¸įæĺİ
    -0.05
    -Dec
    -0.05
    人社
    -0.05
    POSITIVE LOGITS
    ìĸij
    0.06
    jie
    0.06
    ing
    0.05
    ich
    0.05
    ضÙĬØ©
    0.05
    è¤Ĵ
    0.05
     cura
    0.05
     goose
    0.05
    ultiple
    0.05
    aya
    0.05
    Activations Density 0.005%

    No Known Activations