© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 16825
    Prev
    Next
    INDEX
    Explanations

    characters and roles

    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
    عاÙĦ
    -0.06
    纪
    -0.06
    warts
    -0.06
     verified
    -0.05
    undas
    -0.05
    verified
    -0.05
    intas
    -0.05
     sii
    -0.05
    ä¸ĢåĪĢ
    -0.05
    mites
    -0.05
    POSITIVE LOGITS
     design
    0.05
    rol
    0.05
     weights
    0.05
    romatic
    0.05
     roles
    0.05
    name
    0.05
     names
    0.05
    -ending
    0.05
     lá»ĩ
    0.05
     fat
    0.05
    Activations Density 0.008%

    No Known Activations