© 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. 19836
    Prev
    Next
    INDEX
    Explanations

    inmate escape

    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
    uien
    -0.05
    æľ¬æ¬¡ä¼ļè®®
    -0.05
    educt
    -0.05
    uss
    -0.05
    auber
    -0.05
    Targets
    -0.05
    elen
    -0.05
    ä¸Ŀä¸Ŀ
    -0.05
    æݨçIJĨ
    -0.05
    çĶľèľľçļĦ
    -0.05
    POSITIVE LOGITS
     Tages
    0.06
     exercise
    0.06
    维稳
    0.06
     standard
    0.05
    äºij顶
    0.05
    ìĦŃ
    0.05
     longitudinal
    0.05
    Speak
    0.05
     lang
    0.05
     inmate
    0.05
    Activations Density 0.029%

    No Known Activations