© 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. 49724
    Prev
    Next
    INDEX
    Explanations

    along the way

    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
    说æĺ¯
    -0.10
    æł·çļĦ
    -0.10
    oyer
    -0.10
    åĢ¾åIJij
    -0.09
    å½ĵåĪĿ
    -0.09
    éĢĨ
    -0.09
    è¿Ļä¹Ī说
    -0.09
     ÑĨелÑĮÑİ
    -0.08
    ä½łåľ¨
    -0.08
    è¿IJ
    -0.08
    POSITIVE LOGITS
    çļĦä¸ĢäºĽ
    0.13
    è·
    0.10
    åĩºçİ°äºĨ
    0.09
    ä¸Ģ大æī¹
    0.09
    ibern
    0.09
    inders
    0.09
    ãģĦãģıãģ¤ãģĭ
    0.09
    oram
    0.09
    зоÑĢ
    0.09
    ered
    0.09
    Activations Density 0.015%

    No Known Activations