© 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. 18532
    Prev
    Next
    INDEX
    Explanations

    arrays and lists

    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
    lder
    -0.07
    aglia
    -0.06
    ä¼ijåħ»
    -0.06
    åŁ
    -0.06
    üge
    -0.06
    ä¼ij
    -0.06
    kland
    -0.06
     Teig
    -0.06
    åħµ
    -0.06
     gebru
    -0.05
    POSITIVE LOGITS
    boten
    0.06
    nable
    0.05
    able
    0.05
    ادة
    0.05
    åĪ°æĿ¥
    0.05
    ance
    0.05
    ç»ŀ
    0.05
    éĹ
    0.05
     per
    0.05
    æľ¬æĬ¥
    0.05
    Activations Density 0.031%

    No Known Activations