© 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. 17849
    Prev
    Next
    INDEX
    Explanations

    building block source precursor

    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
    بر
    -0.05
    [
    -0.05
    OS
    -0.05
    æĺ¥
    -0.05
    ç¡®
    -0.05
    èĪŁ
    -0.05
    éļĶ
    -0.05
    çĽ¸ä¼¼æĸĩçĮ®
    -0.05
    aster
    -0.05
    çĤ¸
    -0.05
    POSITIVE LOGITS
    åıªæĺ¯åĽłä¸º
    0.06
     renc
    0.06
    æł¹æľ¬æ²¡
    0.06
    erbe
    0.06
    vÃŃo
    0.06
    人æīįå¼ķè¿Ľ
    0.06
    imba
    0.06
    ucks
    0.06
    ullen
    0.06
    大æīĵ
    0.06
    Activations Density 0.001%

    No Known Activations