© 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. 3910
    Prev
    Next
    INDEX
    Explanations

    best services or products

    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
    æľī个
    -0.10
    èĪĮ头
    -0.09
    æµĨ
    -0.08
    é¦ĸä½į
    -0.08
    å¼Ģè¾Ł
    -0.08
    è´µ
    -0.08
    åĪ®
    -0.08
     Emirates
    -0.08
    amination
    -0.08
    ç¼Ŀ
    -0.08
    POSITIVE LOGITS
    çĿ£
    0.10
    好çļĦ
    0.09
    .annotate
    0.09
    leen
    0.09
    ãģĹãģĭãĤĤ
    0.09
    çļĦè·¯ä¸Ĭ
    0.09
    leting
    0.08
    åĮĸåIJĪ
    0.08
    åĪ°ä½į
    0.08
    æ´»è·ĥ
    0.08
    Activations Density 0.049%

    No Known Activations