© 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. 17071
    Prev
    Next
    INDEX
    Explanations

    command-line tools and libraries

    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
    elus
    -0.06
    çİ
    -0.06
     foss
    -0.06
    س
    -0.05
    å½ĵå¹´çļĦ
    -0.05
    è¿ĩ渡
    -0.05
     neg
    -0.05
    à¸Ń
    -0.05
    ×ķ×IJ
    -0.05
    доÑĢа
    -0.05
    POSITIVE LOGITS
    ergen
    0.06
    GUN
    0.06
    ÙıÙĤ
    0.06
    ihen
    0.06
    óln
    0.06
    schen
    0.06
    bud
    0.06
    סת
    0.05
    éĩĮåħĭ
    0.05
    æ·±åħ¥åŁºå±Ĥ
    0.05
    Activations Density 0.013%

    No Known Activations