© 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. 21937
    Prev
    Next
    INDEX
    Explanations

    GOLF, MINNIS, PLUG, HORTON

    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
    uncul
    -0.06
    ones
    -0.06
    uen
    -0.05
    ìĿĺ
    -0.05
    9
    -0.05
    çļĦåĨ³å®ļ
    -0.05
    rag
    -0.05
     souhaitent
    -0.05
    8
    -0.05
    rint
    -0.05
    POSITIVE LOGITS
    i
    0.09
    es
    0.09
    ity
    0.09
    ing
    0.08
    iÅŁ
    0.08
    iha
    0.08
    ição
    0.08
    HORT
    0.08
    ingat
    0.08
    iš
    0.08
    Activations Density 0.038%

    No Known Activations