© 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. 19451
    Prev
    Next
    INDEX
    Explanations

    punctuation and transitions

    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
    à¸ķิà¸Ķà¸ķาม
    -0.06
     ram
    -0.05
     pent
    -0.05
     zob
    -0.05
    æ³½
    -0.05
    ам
    -0.05
     resent
    -0.05
     spell
    -0.05
    ayet
    -0.05
    Mit
    -0.05
    POSITIVE LOGITS
    ido
    0.06
    geois
    0.06
    alc
    0.06
    lie
    0.06
    ä¼ij
    0.06
    åij¨è½¬
    0.06
    IDO
    0.06
    tems
    0.05
    arks
    0.05
    ué
    0.05
    Activations Density 0.001%

    No Known Activations