© 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. 64001
    Prev
    Next
    INDEX
    Explanations

    popup window or dialog box

    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
    æľį
    -0.09
    ä¼ı
    -0.08
    åħį
    -0.08
    è¢į
    -0.08
    lund
    -0.08
    _FLUSH
    -0.08
     Rainbow
    -0.08
    erver
    -0.08
    ivist
    -0.08
    å²³
    -0.08
    POSITIVE LOGITS
    /shared
    0.10
    ãĤ¹ãĥĨ
    0.09
    éļıåį³
    0.09
    ä¸Ģçīĩ
    0.09
    ä¸Ģç³»åĪĹ
    0.09
    æĸ°çļĦä¸Ģ
    0.09
    æľī两ç§į
    0.09
    缪
    0.09
    广éĺĶçļĦ
    0.09
    ombs
    0.08
    Activations Density 0.113%

    No Known Activations