© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19612
    Prev
    Next
    INDEX
    Explanations

    Abu Dhabi

    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
    erie
    -0.06
    eries
    -0.06
    erra
    -0.06
    emberg
    -0.06
    UND
    -0.05
    æĺĨ
    -0.05
    err
    -0.05
    ARI
    -0.05
    ekt
    -0.05
    اÙħ
    -0.05
    POSITIVE LOGITS
    stood
    0.07
    ive
    0.05
     Examples
    0.05
    举ä¾ĭ
    0.05
    alus
    0.05
    ted
    0.05
     examples
    0.05
     Sachs
    0.05
    bing
    0.05
    ayed
    0.05
    Activations Density 0.001%

    No Known Activations