© 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. 17058
    Prev
    Next
    INDEX
    Explanations

    stuffed balls, tomatoes, round

    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
    reak
    -0.06
     logs
    -0.05
     Logs
    -0.05
    åįłæľīçİĩ
    -0.05
    å£
    -0.05
    ÑĤÑĮ
    -0.05
     mat
    -0.05
    æĮ¯
    -0.05
    äºĶæĮĩ
    -0.05
    azza
    -0.05
    POSITIVE LOGITS
    umper
    0.07
     enclosing
    0.07
     redesigned
    0.06
     outer
    0.06
    涤纶
    0.06
    å¤ĸåĮħ
    0.06
     nai
    0.06
    ами
    0.06
    æŀļ
    0.06
    round
    0.06
    Activations Density 0.028%

    No Known Activations