© 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. 18092
    Prev
    Next
    INDEX
    Explanations

    standard library functions

    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
    æģĭ
    -0.10
    åŀ¸
    -0.09
    注éĶĢ
    -0.09
    馬
    -0.09
    çĿĢéĩį
    -0.08
    马æĭī
    -0.08
    诣
    -0.08
    à¹Ĥà¸Ĺ
    -0.08
    uers
    -0.08
    ä¸įæĪIJ
    -0.08
    POSITIVE LOGITS
    æłĩåĩĨ
    0.11
     standard
    0.11
    è¿Ļå¥Ĺ
    0.11
    -standard
    0.10
    æ¨Ļæºĸ
    0.10
    ä½ľåĩºäºĨ
    0.09
    çĥĤ
    0.09
    è±IJå¯Į
    0.09
    丰å¯Į
    0.09
    åħ¬çĽĬ
    0.09
    Activations Density 0.605%

    No Known Activations