© 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. 20639
    Prev
    Next
    INDEX
    Explanations

    wearing clothes on body

    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
    agine
    -0.07
    voli
    -0.06
    管æīĢ
    -0.06
     wideo
    -0.06
    amore
    -0.06
     Quello
    -0.06
     yerine
    -0.06
     Ðĵолов
    -0.06
    对èģĶ
    -0.06
    .erb
    -0.06
    POSITIVE LOGITS
     lẫn
    0.05
     transport
    0.05
     transfer
    0.05
    éĿ¢çĽ®
    0.05
    aken
    0.05
    è½½
    0.05
    çļĦæĸ¹æ³ķåĴĮ
    0.05
    len
    0.05
     test
    0.05
     record
    0.05
    Activations Density 0.013%

    No Known Activations