© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 60810
    Prev
    Next
    INDEX
    Explanations

    kind of

    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
    Negative Logits
    éĶ¥
    -0.09
    è§ĤçĤ¹
    -0.09
    æĤĮ
    -0.08
    åĶ¯ä¸Ģ
    -0.08
    ç¾²
    -0.08
    fant
    -0.08
     пÑĥнк
    -0.08
     dub
    -0.08
    ä¼Ĭæĭī
    -0.08
    éĴ
    -0.08
    POSITIVE LOGITS
    isia
    0.09
    иÑĩно
    0.09
    çļĦéĤ£ç§į
    0.09
    ISING
    0.09
    äºĪ
    0.08
     Bren
    0.08
    è¿ĻäºĽéĹ®é¢ĺ
    0.08
    ä¸įä¸Ĭ
    0.08
    ä¸įèĪį
    0.08
    çħī
    0.08
    Activations Density 0.036%

    No Known Activations