© 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. 18908
    Prev
    Next
    INDEX
    Explanations

    one of the

    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
    istic
    -0.07
    uring
    -0.06
    PY
    -0.06
    erry
    -0.06
    öv
    -0.06
    urus
    -0.06
    ä¸įè¿ĩåľ¨
    -0.06
    inen
    -0.06
    isit
    -0.06
    bite
    -0.06
    POSITIVE LOGITS
     among
    0.07
    åIJĮ
    0.06
    Tre
    0.06
     Among
    0.06
    Among
    0.06
     ÑģÑĢеди
    0.06
     Tre
    0.06
    éĥ¨åĪĨ
    0.06
    among
    0.06
    tre
    0.06
    Activations Density 0.089%

    No Known Activations