© 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. 21380
    Prev
    Next
    INDEX
    Explanations

    names followed by punctuation or titles

    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
    eve
    -0.05
    omo
    -0.05
    -of
    -0.05
    ipur
    -0.05
    pur
    -0.04
     somehow
    -0.04
    ison
    -0.04
    çIJĨ解çļĦ
    -0.04
    ofi
    -0.04
    +
    -0.04
    POSITIVE LOGITS
    ught
    0.06
     metu
    0.06
    rices
    0.06
    élix
    0.06
    betul
    0.06
    ÑĥÑīе
    0.06
    tees
    0.06
    çĤ¹ä¸Ĭ
    0.06
    åĬ¨åĬĽæĸ¹éĿ¢
    0.06
    建æĪIJ
    0.06
    Activations Density 0.002%

    No Known Activations