© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 4572
    Prev
    Next
    INDEX
    Explanations

    quotes and quotations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    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
     Mana
    -0.09
    å°¾
    -0.08
     slick
    -0.08
    ulet
    -0.08
    ä¸ŃåİŁ
    -0.08
     narr
    -0.08
    äs
    -0.08
    以èī²
    -0.08
    Susp
    -0.08
    éĢļ
    -0.08
    POSITIVE LOGITS
     quotes
    0.15
     Quotes
    0.14
    è¿Ļåı¥è¯Ŀ
    0.14
    _quote
    0.13
     quote
    0.13
    Quotes
    0.12
    .quote
    0.12
    æĬ¥ä»·
    0.12
    quotes
    0.12
     quotation
    0.11
    Activations Density 0.066%

    No Known Activations