© 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. 18959
    Prev
    Next
    INDEX
    Explanations

    onCreate(Bundle savedInstanceState)

    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
    andai
    -0.07
    à¸į
    -0.06
    å¹´èĩ³ä»Ĭ
    -0.06
    pics
    -0.06
    riba
    -0.06
    ìĸ¸
    -0.06
    emudi
    -0.06
    为主çļĦ
    -0.06
    .weixin
    -0.06
    以å®ŀéĻħè¡ĮåĬ¨
    -0.05
    POSITIVE LOGITS
    icha
    0.05
    éģį
    0.05
    éĥ¨
    0.05
    åįĵ
    0.05
     defeats
    0.05
    oor
    0.05
    é»ijçĻ½
    0.05
    uro
    0.05
    æĹ¥å¸¸ç®¡çIJĨ
    0.05
    èµ°éģį
    0.05
    Activations Density 0.001%

    No Known Activations