© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 20717
    Prev
    Next
    INDEX
    Explanations

    sugar, sweets, calories

    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
    éģĵéģĵ
    -0.07
    ählen
    -0.06
    /ns
    -0.06
    åѦæ³ķ
    -0.06
    ective
    -0.06
    tese
    -0.06
    rens
    -0.06
    模å¼ıä¸Ń
    -0.06
     pouc
    -0.06
    ãĤ·ãĤ¢
    -0.06
    POSITIVE LOGITS
    é¼ĵ
    0.06
    æķ¬
    0.05
    ff
    0.05
    G
    0.05
    ck
    0.05
     drum
    0.05
     raff
    0.05
    u
    0.05
    éļıæľº
    0.05
    iu
    0.05
    Activations Density 0.002%

    No Known Activations