© 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. 19591
    Prev
    Next
    INDEX
    Explanations

    punctuation followed by conjunctions

    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
     Exact
    -0.06
     bipartisan
    -0.05
    ibar
    -0.05
     XXL
    -0.05
    åĪĴ
    -0.05
    гоÑĢа
    -0.05
    olib
    -0.05
    est
    -0.05
    ovens
    -0.05
    åĮĸæĪIJ
    -0.05
    POSITIVE LOGITS
    ritis
    0.06
     prospect
    0.06
    aign
    0.05
     marge
    0.05
     polish
    0.05
    akas
    0.05
     seize
    0.05
    ÄĹti
    0.05
    ./.
    0.05
    ence
    0.05
    Activations Density 0.048%

    No Known Activations