© 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. 39357
    Prev
    Next
    INDEX
    Explanations

    abbreviation definitions or explanations

    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
    æĭĶ
    -0.10
    éľīç´ł
    -0.08
    让å®ĥ
    -0.08
    禺
    -0.08
    身边çļĦ
    -0.08
    身边
    -0.08
    è§īå¾Ĺèĩªå·±
    -0.08
    exist
    -0.08
    åħīæĺİ
    -0.08
    è§īå¾Ĺ
    -0.08
    POSITIVE LOGITS
    æĺ¯æĮĩ
    0.14
    æĮĩçļĦæĺ¯
    0.14
    æĮĩ
    0.10
    å½ĵä½ł
    0.10
     refers
    0.09
    åľ¨è¿ĩ渡
    0.09
    ä¹Łä¸įåı¯èĥ½
    0.09
    ä¾Ŀçħ§
    0.09
    Term
    0.09
    .term
    0.09
    Activations Density 0.125%

    No Known Activations