© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20278
    Prev
    Next
    INDEX
    Explanations

    postal codes and identifiers

    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
    enne
    -0.08
    éĥ¨
    -0.08
    èºģ
    -0.08
    æ¦ī
    -0.08
    æݧèĤ¡éĽĨåĽ¢
    -0.08
    BJ
    -0.07
    è¶ĬæĿ¥
    -0.07
    飧
    -0.07
    纳åħ¥
    -0.07
     же
    -0.07
    POSITIVE LOGITS
    æľ¬è´¨ä¸Ĭ
    0.10
    IED
    0.10
    èī¯
    0.10
    .mit
    0.09
    çĢ¼
    0.09
     undermin
    0.09
    оÑĨен
    0.08
    -Saharan
    0.08
    羣æĺ¯å¤ª
    0.08
    ç¾İå¦Ļ
    0.08
    Activations Density 0.253%

    No Known Activations