© 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. 19277
    Prev
    Next
    INDEX
    Explanations

    plural nounscompaniesvitaminshormones

    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
    ometown
    -0.07
    iovas
    -0.06
    æķ°ä¸º
    -0.06
    ocen
    -0.06
     Å¡te
    -0.06
    usband
    -0.06
    #${
    -0.06
    æķ°çļĦ
    -0.06
    ocu
    -0.06
     Environ
    -0.06
    POSITIVE LOGITS
    主è¦ģçļĦ
    0.06
    ëŀij
    0.05
    inkle
    0.05
    her
    0.05
    ä¸ĩå·¦åı³
    0.05
    ÑĪеÑĢ
    0.05
    ulich
    0.05
    让åIJĮåѦ们
    0.05
    åħ¶ä»ĸçļĦ
    0.05
    éĻ£
    0.04
    Activations Density 0.212%

    No Known Activations