© 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. 20013
    Prev
    Next
    INDEX
    Explanations

    medical conditions and remedies

    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
    igan
    -0.06
    онеÑĢ
    -0.06
    çĿ£
    -0.05
    iertas
    -0.05
    resent
    -0.05
    alas
    -0.05
    ott
    -0.05
     backwards
    -0.05
     conf
    -0.05
    ider
    -0.05
    POSITIVE LOGITS
    èĭ¥æĥ³
    0.06
    èĻ½æľī
    0.06
     kuulu
    0.06
    对ä¸Ĭ
    0.06
     quizá
    0.06
    ä¼ļæĽ´
    0.05
    åIJ«æ°´
    0.05
    amble
    0.05
    æĬĵå®ŀ
    0.05
    ä¿©
    0.05
    Activations Density 0.190%

    No Known Activations