© 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. 21246
    Prev
    Next
    INDEX
    Explanations

    fatty acids

    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
    ãģįãģ®
    -0.06
    ebin
    -0.05
    alih
    -0.05
    Fir
    -0.05
    Ñĥб
    -0.05
    enzo
    -0.05
    меннÑĭй
    -0.05
     Anal
    -0.05
    wer
    -0.05
    pag
    -0.05
    POSITIVE LOGITS
    sole
    0.06
    RA
    0.06
    ser
    0.06
     versatile
    0.05
    ج
    0.05
    velt
    0.05
    QUEUE
    0.05
     moc
    0.05
    æī©å±ķèµĦæĸĻ
    0.05
    à¹ģà¸Ĺà¹ī
    0.05
    Activations Density 0.002%

    No Known Activations