© 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. 20926
    Prev
    Next
    INDEX
    Explanations

    stream and collection types

    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
    nene
    -0.06
    èıģ
    -0.05
    ENDING
    -0.05
     roup
    -0.05
    anju
    -0.05
    ról
    -0.05
    Piece
    -0.05
    perk
    -0.05
    ijo
    -0.05
     cou
    -0.05
    POSITIVE LOGITS
    èĢĮ代ä¹ĭ
    0.06
    agr
    0.06
    itata
    0.06
    æł·
    0.05
    æģį
    0.05
    åĽ½åĬ¡
    0.05
    ativer
    0.05
    á
    0.05
    abo
    0.05
    æĹłå¤Ħä¸įåľ¨
    0.05
    Activations Density 0.050%

    No Known Activations