© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 21237
    Prev
    Next
    INDEX
    Explanations

    Develop growth and skills

    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
    iegel
    -0.06
     potable
    -0.05
    hek
    -0.05
    æķĪæŀľæĽ´å¥½
    -0.05
    伶ä¿IJ
    -0.05
     specifie
    -0.05
     عزÛĮز
    -0.05
    è´´åIJĪ
    -0.05
    bol
    -0.05
    ieux
    -0.05
    POSITIVE LOGITS
    reon
    0.06
    ROT
    0.05
    ä¸įå®Į
    0.05
    åľ¨åħ¶ä»ĸ
    0.05
    延
    0.05
    ä¹ĭä¸ĢçļĦ
    0.05
     Pins
    0.05
    uten
    0.05
    RACT
    0.05
    æĪIJ为
    0.05
    Activations Density 0.006%

    No Known Activations