© 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. 20602
    Prev
    Next
    INDEX
    Explanations

    paying attention

    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
    inj
    -0.06
    å¢Ł
    -0.06
    haar
    -0.06
    è¿Ķ
    -0.06
     counter
    -0.06
    æĬ¹
    -0.06
    aner
    -0.06
    orton
    -0.06
    lox
    -0.06
    ä¸Ĭæŀ¶
    -0.06
    POSITIVE LOGITS
    åIJ¬è®²
    0.06
    æŶæ¯ı
    0.06
    save
    0.06
    AsString
    0.06
    yme
    0.06
    üt
    0.06
     attent
    0.06
     kidnapping
    0.05
    zip
    0.05
    yps
    0.05
    Activations Density 0.003%

    No Known Activations