© 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. 22333
    Prev
    Next
    INDEX
    Explanations

    those resources

    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
    olat
    -0.05
    ington
    -0.05
    éĽĢ
    -0.05
    shed
    -0.05
    alia
    -0.05
    igungs
    -0.05
    ilhas
    -0.05
    ÃŃr
    -0.05
    HER
    -0.05
    è¯Ń
    -0.05
    POSITIVE LOGITS
     kaut
    0.06
    åģļçļĦå°±æĺ¯
    0.05
    évÅij
    0.05
    andu
    0.05
    人åķĬ
    0.05
     Ink
    0.05
    -sm
    0.05
    rive
    0.05
    vy
    0.05
    ócr
    0.05
    Activations Density 0.080%

    No Known Activations