© 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. 18656
    Prev
    Next
    INDEX
    Explanations

    medical devices and applications

    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
    atak
    -0.05
    åĶ¤
    -0.05
    atab
    -0.05
     exhaust
    -0.05
    ain
    -0.05
     Qu
    -0.05
     cú
    -0.05
    è°ĥ
    -0.04
    di
    -0.04
    salt
    -0.04
    POSITIVE LOGITS
    åĮ»çĸĹåĻ¨æ¢°
    0.08
    æĤ£èĢħ
    0.07
     gore
    0.07
    æ¤įåħ¥
    0.07
    èĤ¢
    0.07
    pliant
    0.07
    åīĸèħ¹
    0.07
    fid
    0.07
    åĻ¨æ¢°
    0.07
    æ±Ĥæĺ¯
    0.07
    Activations Density 0.121%

    No Known Activations