© 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. 20966
    Prev
    Next
    INDEX
    Explanations

    months of the year

    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
     oppos
    -0.07
    ydi
    -0.06
    yanto
    -0.06
    éĩij森
    -0.06
    BOSE
    -0.06
    å¹´æĪIJç«ĭ
    -0.06
    ju
    -0.06
    зоÑĢом
    -0.06
    yson
    -0.06
     sunshine
    -0.05
    POSITIVE LOGITS
    æľŁæ»¡
    0.05
    ç´ł
    0.05
    angers
    0.05
    ↵
    0.05
    uk
    0.05
    rus
    0.05
    App
    0.05
    åıł
    0.05
    astre
    0.05
    èĮĥåĽ´å¹¿
    0.04
    Activations Density 0.014%

    No Known Activations