© 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. 17009
    Prev
    Next
    INDEX
    Explanations

    U.S. Pat. No

    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
    æĮij
    -0.06
    ijin
    -0.06
    bud
    -0.05
    ÑĦоÑĢ
    -0.05
     vera
    -0.05
    ÑĮев
    -0.05
    Nickname
    -0.05
    çļĦåį°è±¡
    -0.05
    aleb
    -0.05
    /-
    -0.05
    POSITIVE LOGITS
    ç¾ŀ
    0.07
    ings
    0.06
    æĽ´æ²¡æľī
    0.06
    hausen
    0.06
     gerecht
    0.05
    åĬłè½½æĽ´å¤ļ
    0.05
    acles
    0.05
    orz
    0.05
    à¸Ĺà¹īà¸Ńà¸ĩ
    0.05
    cripciones
    0.05
    Activations Density 0.001%

    No Known Activations