© 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. 1557
    Prev
    Next
    INDEX
    Explanations

    numbered lists or sequences

    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
    æĸ¹æĸ¹éĿ¢éĿ¢
    -0.10
    åIJĦ个æĸ¹éĿ¢
    -0.10
    incy
    -0.10
    骡
    -0.10
     needles
    -0.09
    æ¾Ī
    -0.09
    .metro
    -0.09
    å»¶æľŁ
    -0.09
    äge
    -0.09
    æ¶Ī
    -0.09
    POSITIVE LOGITS
    ç¼ĸåı·
    0.22
    åı·
    0.22
    åı·çłģ
    0.20
     номеÑĢ
    0.16
    èĻŁ
    0.15
     numbered
    0.15
    çķª
    0.14
    ë²Īíĺ¸
    0.14
    -number
    0.14
     numéro
    0.13
    Activations Density 0.256%

    No Known Activations