© 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. 59458
    Prev
    Next
    INDEX
    Explanations

    opening or reopening

    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
    åİĿ
    -0.10
    æĮģãģ¡
    -0.10
    à¹Į
    -0.09
    æıĨ
    -0.09
    ancock
    -0.09
    èĭ«
    -0.09
    ä¿ĿçķĻ
    -0.08
    å½ķåħ¥
    -0.08
     pov
    -0.08
    inant
    -0.08
    POSITIVE LOGITS
    OrUpdate
    0.10
    æĢĢæĬ±
    0.09
    tn
    0.09
    å¾ĭ
    0.08
    åĶĨ
    0.08
    åİĨåı²æĸ°
    0.08
    agnar
    0.08
    å¨ĺ
    0.08
    äºĺ
    0.08
    æĦ¿æĦı
    0.07
    Activations Density 0.035%

    No Known Activations