© 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. 21600
    Prev
    Next
    INDEX
    Explanations

    HTML and CSS code

    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
    conde
    -0.07
    以å°ı
    -0.07
    uca
    -0.06
    arel
    -0.06
    ä¿ĿæĮģé«ĺ度
    -0.06
     crank
    -0.06
    æĪĸ以åħ¶ä»ĸæĸ¹å¼ı
    -0.06
    å¤ļç§įå½¢å¼ı
    -0.06
    fuÃŁ
    -0.06
    转åŀĭåıijå±ķ
    -0.06
    POSITIVE LOGITS
    éĢĤ
    0.06
     dem
    0.05
    umos
    0.05
    å¿ħ
    0.05
    .au
    0.05
    UNA
    0.05
    æł¹æľ¬
    0.05
     trist
    0.04
    åħ¨åĽ½æĸĩæĺİåŁİå¸Ĥ
    0.04
    åIJĥåĬĽ
    0.04
    Activations Density 0.014%

    No Known Activations