© 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. 53014
    Prev
    Next
    INDEX
    Explanations

    quotidian

    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
    èĵĦ
    -0.10
    anny
    -0.10
    lessly
    -0.10
    åĵĨ
    -0.09
    ogg
    -0.09
     ÃŃt
    -0.09
    acam
    -0.09
    çħ³
    -0.09
    ä¹ĺ车
    -0.08
    апÑĢ
    -0.08
    POSITIVE LOGITS
    éĿŀ常åĸľæ¬¢
    0.09
    è´¨éĩıéĹ®é¢ĺ
    0.09
    zell
    0.08
    æĢİä¹Īèĥ½
    0.08
    æİī
    0.08
    èļĢ
    0.08
    æĩĭ
    0.08
    æİīäºĨ
    0.08
    马ä¸Ĭ
    0.08
    èĪ¬çļĦ
    0.08
    Activations Density 0.421%

    No Known Activations