© 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. 5931
    Prev
    Next
    INDEX
    Explanations

    check if exists

    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
    è¾Ļ
    -0.11
    å¼
    -0.10
    éĢł
    -0.09
    éĵ¨
    -0.09
    ä¾ĽåĽ¾
    -0.09
    rack
    -0.09
    æ´ģçĻ½
    -0.08
    æľ¬ç«Ļ
    -0.08
    èģĮèĥ½éĥ¨éŨ
    -0.08
    ãĥĥãĤ¯
    -0.08
    POSITIVE LOGITS
    .strings
    0.09
    éĹ®çŃĶ
    0.09
    -Series
    0.09
    èĿī
    0.09
    ALLE
    0.08
    çĶ·å£«
    0.08
    ợi
    0.08
    Williams
    0.08
    èİŀ
    0.08
    Ṭ
    0.08
    Activations Density 0.013%

    No Known Activations