© 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. 49338
    Prev
    Next
    INDEX
    Explanations

    top followed by numbers

    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
    å¾Īå¤ļäºĭæĥħ
    -0.10
    yne
    -0.09
    ä¹Łæĺ¯ä¸Ģ个
    -0.09
    elong
    -0.08
    æĤ£
    -0.08
    çī¹æ®ĬæĥħåĨµ
    -0.08
    çĤ¹å¤ļ
    -0.08
    ẻ
    -0.08
    强åĮĸ
    -0.08
    SY
    -0.08
    POSITIVE LOGITS
    åīįåįģ
    0.14
    TOP
    0.13
     top
    0.13
     TOP
    0.12
    æİĴåIJį
    0.11
     Top
    0.11
    åįģæĿ¡
    0.11
    æ¦ľ
    0.11
    _TOP
    0.11
    (top
    0.11
    Activations Density 0.086%

    No Known Activations