© 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. 21044
    Prev
    Next
    INDEX
    Explanations

    names and numbers

    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
    -
    -0.05
    oose
    -0.05
    (
    -0.05
    wish
    -0.05
    "
    -0.04
    acus
    -0.04
    ság
    -0.04
    ä¸İ该
    -0.04
    pas
    -0.04
    CM
    -0.04
    POSITIVE LOGITS
    rach
    0.06
    tourn
    0.06
    åķĨæłĩä¿¡æģ¯
    0.06
    лÑĮнÑĸ
    0.06
    uelles
    0.06
    onar
    0.06
    nÄĻ
    0.06
    为çݩ家
    0.06
    éķľæ£ĢæŁ¥
    0.06
    ersp
    0.06
    Activations Density 0.007%

    No Known Activations