© 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. 21262
    Prev
    Next
    INDEX
    Explanations

    wide or broad scope

    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
    们
    -0.07
    ä¸įä¼ij
    -0.05
     ÑĨел
    -0.05
    Ñģкле
    -0.05
    åĵģçļĦ
    -0.05
    éĤ£åı¥è¯Ŀ
    -0.05
     ÙĥÙĦÙĩ
    -0.05
    inz
    -0.05
    ä¸įæĥ§
    -0.05
    вода
    -0.05
    POSITIVE LOGITS
    aldi
    0.07
    вÑĮÑİ
    0.07
    aland
    0.06
    ÙĪس
    0.06
    bred
    0.06
    Ùģض
    0.06
    atamente
    0.06
    ÙĪØ©
    0.06
     Seeder
    0.06
    .mit
    0.06
    Activations Density 0.017%

    No Known Activations