© 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. 21218
    Prev
    Next
    INDEX
    Explanations

    biological and scientific concepts

    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
    (
    -0.05
     ch
    -0.05
    ç³»
    -0.04
    ثر
    -0.04
    lier
    -0.04
    ice
    -0.04
    èĨľ
    -0.04
    åºĶè¿IJ
    -0.04
    åĸĦ
    -0.04
     ÙħØŃ
    -0.04
    POSITIVE LOGITS
    azon
    0.07
     <+
    0.07
     #__
    0.06
    eting
    0.06
    :index
    0.06
    ä¸ĭè§Ĵ
    0.06
     angk
    0.06
     INTERFACE
    0.06
    æ¡Īåıij
    0.06
     kend
    0.06
    Activations Density 0.098%

    No Known Activations