© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 18612
    Prev
    Next
    INDEX
    Explanations

    my dear, my god

    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
    å·²çŁ¥
    -0.06
    åħ¶ä»ĸ
    -0.06
    -0.05
     known
    -0.05
    known
    -0.05
    ä¸įåIJĮçļĦ
    -0.05
     called
    -0.05
    ç«Ļ
    -0.05
    ee
    -0.05
    ologic
    -0.05
    POSITIVE LOGITS
    ä¸ĩä¸ĩ
    0.06
    å¤ĩå¿ĺ
    0.06
     пÑĢеÑģÑĤ
    0.06
    skal
    0.06
    krim
    0.06
    aum
    0.06
     **âĢ¢
    0.06
    å¸Ĥæĸ°
    0.06
     giapp
    0.06
    avic
    0.06
    Activations Density 0.001%

    No Known Activations