© 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. 21525
    Prev
    Next
    INDEX
    Explanations

    code, math, and sets involving X

    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
    å¸Į
    -0.06
    amespace
    -0.05
     sized
    -0.05
    ––
    -0.05
     vo
    -0.05
    toast
    -0.05
    icule
    -0.05
    ]+\
    -0.05
    æĸ¹æŃ£
    -0.05
    siÄĻ
    -0.05
    POSITIVE LOGITS
    ä¸įæĢ¥
    0.06
    agua
    0.06
    çķª
    0.06
    ienda
    0.06
    对äºİéĤ£äºĽ
    0.06
    atera
    0.05
    orta
    0.05
    лаг
    0.05
    åĪĨåŃIJçļĦ
    0.05
    æİĸ
    0.05
    Activations Density 0.001%

    No Known Activations