© 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. 17409
    Prev
    Next
    INDEX
    Explanations

    live crowd healthcare device restrictions

    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
    agné
    -0.06
     impi
    -0.06
     daÃŃ
    -0.06
    iosi
    -0.06
    اÙĨÛĮ
    -0.06
    olari
    -0.06
     garanzia
    -0.06
     cias
    -0.06
    æķ´é«Ķ
    -0.06
     overall
    -0.06
    POSITIVE LOGITS
    è§ī
    0.06
    è¢
    0.05
    quist
    0.05
    /ss
    0.05
     Pros
    0.05
    ater
    0.05
    orrh
    0.05
    erein
    0.05
    çŀ
    0.05
    Âł
    0.05
    Activations Density 0.040%

    No Known Activations