© 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. 20022
    Prev
    Next
    INDEX
    Explanations

    lists examples with punctuation

    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
    ãģ¤ãģ¤
    -0.06
    veiller
    -0.06
    ertas
    -0.06
    hest
    -0.06
    Ñħодим
    -0.06
    ponder
    -0.05
    ÐŁÐ¾Ð´ÑĢоб
    -0.05
    mens
    -0.05
     ÐĿаиб
    -0.05
    ,:,:
    -0.05
    POSITIVE LOGITS
     forth
    0.05
    tel
    0.05
    esp
    0.05
    æķĻèĤ²æĺ¯
    0.05
    بار
    0.05
    igl
    0.05
     out
    0.05
    ream
    0.05
     til
    0.05
    kla
    0.05
    Activations Density 0.073%

    No Known Activations