© 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. 18841
    Prev
    Next
    INDEX
    Explanations

    a better place

    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
    åħīæĺİçļĦ
    -0.06
     outs
    -0.06
    æģ¤
    -0.05
    íĮIJ
    -0.05
     anymore
    -0.05
    çľ
    -0.05
    å¾Īé«ĺçļĦ
    -0.05
    invoices
    -0.05
    etros
    -0.05
    unj
    -0.05
    POSITIVE LOGITS
    ÏĦÎŃÏģ
    0.06
    å¢ŀéĩı
    0.06
    âĺĨ
    0.06
    å¢ŀæ·»
    0.05
     jem
    0.05
     incremental
    0.05
     increment
    0.05
    خاÙĦ
    0.05
    crement
    0.05
    æĪĸ许æľī
    0.05
    Activations Density 0.005%

    No Known Activations