© 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. 22139
    Prev
    Next
    INDEX
    Explanations

    founder/company/organization founder

    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
    vice
    -0.05
     embedded
    -0.05
    oug
    -0.05
    èݲ
    -0.05
     stor
    -0.05
    è°£
    -0.05
    åī²ãĤĬ
    -0.05
    éĢıéľ²
    -0.05
    specific
    -0.05
     internal
    -0.05
    POSITIVE LOGITS
    cil
    0.07
    ä¸Ģ个å°ı
    0.06
    ä¸Ģ个æĸ°çļĦ
    0.06
    ÑĢÑĸв
    0.06
    ÄįiÄĩ
    0.06
     afterwards
    0.06
     pinterest
    0.06
    PixelFormat
    0.06
     Canti
    0.06
     ëľ»ìĿĦ
    0.06
    Activations Density 0.164%

    No Known Activations