© 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. 16922
    Prev
    Next
    INDEX
    Explanations

    button, RUN, Be

    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
    åĩĿ
    -0.06
     photos
    -0.05
    åıijçĶŁçļĦ
    -0.05
    æľīæĪij
    -0.05
     vill
    -0.05
    æľĢ大åĮĸ
    -0.05
    اÛĮت
    -0.05
     تتÙħÙĥÙĨ
    -0.05
     bonne
    -0.05
    éĩį建
    -0.05
    POSITIVE LOGITS
    isión
    0.06
    antung
    0.06
     amid
    0.06
    æµģéĢļ
    0.06
    symbol
    0.06
    aped
    0.06
    综åIJĪæĶ¹éĿ©
    0.06
    ringe
    0.06
    менÑĮ
    0.06
    mination
    0.06
    Activations Density 0.001%

    No Known Activations