© 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. 20389
    Prev
    Next
    INDEX
    Explanations

    testosterone, history, technology

    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
     Ø£ÙĬÙĨ
    -0.06
     tr
    -0.05
    utu
    -0.05
     desliz
    -0.05
    èĬ±éĥ½
    -0.05
     веÑĢно
    -0.05
    elum
    -0.05
    zem
    -0.05
     tuh
    -0.05
     trust
    -0.05
    POSITIVE LOGITS
    ise
    0.06
    eca
    0.06
    ä¸ĵçĶ¨çļĦ
    0.06
    jan
    0.06
     boobs
    0.05
     Separate
    0.05
    ulas
    0.05
    åĮ»ç§ij大åѦéĻĦå±ŀ
    0.05
    ury
    0.05
    æIJŀ
    0.05
    Activations Density 0.077%

    No Known Activations