© 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. 22027
    Prev
    Next
    INDEX
    Explanations

    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
    ÙĩÙĨ
    -0.08
    oroz
    -0.07
    ä¼łæĿ¥äºĨ
    -0.06
    ساÙħ
    -0.06
    rious
    -0.06
    åĨħèĴĻ
    -0.06
    ewnÄĻ
    -0.06
     resultar
    -0.06
    ä¸ĢåĽŀäºĭ
    -0.06
     Somehow
    -0.06
    POSITIVE LOGITS
     '
    0.05
    omp
    0.05
    T
    0.05
    ç¬ij
    0.05
     die
    0.04
     da
    0.04
     sent
    0.04
    {T
    0.04
     grat
    0.04
     Both
    0.04
    Activations Density 0.023%

    No Known Activations