© 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. 20964
    Prev
    Next
    INDEX
    Explanations

    unique properties

    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
    åĸĦ
    -0.06
    éģĵ
    -0.05
    èĺ
    -0.05
    unt
    -0.05
    acer
    -0.05
    æ¯į
    -0.05
    orr
    -0.05
    ä¸ŃéĢļ
    -0.05
    anness
    -0.05
     поÑģад
    -0.05
    POSITIVE LOGITS
    éĿŀ常ä¸įéĶĻ
    0.06
    endid
    0.06
    grade
    0.06
    éĻ¢éķ·
    0.06
    æľīå¥ĸ
    0.06
    ynet
    0.06
    stav
    0.06
    -corner
    0.06
    åıĪæĪĸèĢħ
    0.06
    rops
    0.06
    Activations Density 0.006%

    No Known Activations