© 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. 54757
    Prev
    Next
    INDEX
    Explanations

    and/or before specifications/complaints/need/costs/filter/media/research

    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
    æĸĩ书
    -0.10
    æµĴ
    -0.10
    eree
    -0.09
    åľ°éģĵ
    -0.09
    å§ij
    -0.09
    çķª
    -0.09
    ä¸į顾
    -0.09
    åºľ
    -0.09
    orda
    -0.09
    .grade
    -0.09
    POSITIVE LOGITS
    è¦ģ说
    0.10
    对æ¯Ķ
    0.08
     Bert
    0.08
     Marr
    0.08
     identifiable
    0.08
    uant
    0.08
    è°Ľ
    0.08
    æĢĢæĬ±
    0.08
     Cata
    0.08
    å»·
    0.08
    Activations Density 0.002%

    No Known Activations