© 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. 5872
    Prev
    Next
    INDEX
    Explanations

    parts of objects

    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
     itself
    -0.09
    inha
    -0.09
    人éĢł
    -0.09
    ä¹Łæĺ¯ä¸Ģ个
    -0.09
    odem
    -0.08
    顺çķħ
    -0.08
    å±ŀäºİèĩªå·±
    -0.08
    æĿĤçī©
    -0.08
    é¾Ł
    -0.08
    dain
    -0.08
    POSITIVE LOGITS
    å¾Īæ¼Ĥ亮
    0.10
    åİĿ
    0.10
    å¾Īæ£Ĵ
    0.10
    äºĨåĩł
    0.09
     millennium
    0.09
    å¾Ĺå¾Ī
    0.09
    äºĨåIJĹ
    0.09
    çļĦåŃĺåľ¨
    0.09
    çļĦåīįæıIJä¸ĭ
    0.09
    äºĨä¸ĢäºĽ
    0.09
    Activations Density 0.145%

    No Known Activations