© 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. 20202
    Prev
    Next
    INDEX
    Explanations

    computing devices

    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
     Kül
    -0.06
    åīįæľŁçļĦ
    -0.05
    athom
    -0.05
    ouri
    -0.05
    æľīä½į
    -0.05
    ucha
    -0.05
    elaar
    -0.05
    并æıIJåĩº
    -0.05
    åīįæľŁ
    -0.05
    ä¸Ĭéĥ¨
    -0.05
    POSITIVE LOGITS
    ãĢħ
    0.06
    é¢ĸ
    0.06
    èĸ
    0.06
     zob
    0.06
    æıĴ
    0.05
    osos
    0.05
     Conex
    0.05
    ówno
    0.05
    ãĢħãģ¯
    0.05
     ë³´ìĿ´ì§Ģ
    0.05
    Activations Density 0.067%

    No Known Activations