© 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. 19087
    Prev
    Next
    INDEX
    Explanations

    biblical figures

    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
     version
    -0.06
    欲
    -0.06
    åĢĴ
    -0.06
    omal
    -0.05
    ç«ĭéĿ¢
    -0.05
     perspective
    -0.05
     Sprache
    -0.05
     Version
    -0.05
    æİĴ
    -0.05
    perienced
    -0.05
    POSITIVE LOGITS
    udge
    0.06
    Ùħد
    0.06
     eid
    0.06
    imits
    0.06
    itis
    0.06
    è¿ĩåIJİ
    0.05
    å¤ļè¾¹
    0.05
     Fons
    0.05
    chet
    0.05
    åľ¨ä¸ĸ
    0.05
    Activations Density 0.019%

    No Known Activations