© 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. 63852
    Prev
    Next
    INDEX
    Explanations

    gone by

    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
    wide
    -0.10
    down
    -0.10
    ï¸ı
    -0.09
    landers
    -0.09
    ç¾¹
    -0.09
    inq
    -0.08
    name
    -0.08
    amp
    -0.08
    work
    -0.08
    à¹Į
    -0.08
    POSITIVE LOGITS
    æİīäºĨ
    0.10
    åħĪæĺ¯
    0.10
    æİī
    0.10
    ecom
    0.10
    éĢĿ
    0.09
    æ¶İ
    0.09
    æĹłå£°
    0.09
    ental
    0.09
    å·²ä¹ħçļĦ
    0.09
    åıijå±ķæľºéģĩ
    0.09
    Activations Density 0.010%

    No Known Activations