© 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. 18435
    Prev
    Next
    INDEX
    Explanations

    code structure syntax

    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
    auc
    -0.06
    ure
    -0.06
    eder
    -0.06
    æ¨
    -0.05
    Ùĩر
    -0.05
    ä½ķ为
    -0.05
    åħĪæĿ¥
    -0.05
    ber
    -0.05
    a
    -0.05
    ä»»ä½ķä¸Ģç§į
    -0.05
    POSITIVE LOGITS
    åı®
    0.06
    ç³Ł
    0.06
    dami
    0.06
    女çļĦ
    0.06
    åİķ
    0.06
    åŃIJçļĦ
    0.06
     Browns
    0.06
    å¦ĩç§ijåĮ»éĻ¢
    0.06
    idges
    0.05
    è¿ħ
    0.05
    Activations Density 0.012%

    No Known Activations