© 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. 16912
    Prev
    Next
    INDEX
    Explanations

    can't or can + verb

    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
    _closure
    -0.09
     hé
    -0.09
    تس
    -0.08
    æĮ
    -0.08
    UNC
    -0.08
    inka
    -0.08
    强è¡Į
    -0.08
    æ·ĺ
    -0.08
    plug
    -0.08
    ills
    -0.08
    POSITIVE LOGITS
    å¿įåıĹ
    0.12
    æĦŁè§īåĪ°
    0.12
    å¾Īæĸ¹ä¾¿
    0.11
    çľĭåĪ°äºĨ
    0.10
    æĥij
    0.10
    çľĭä¸įæĩĤ
    0.10
    没æľīæĥ³åĪ°
    0.09
    çľĭè§ģ
    0.09
    ç¢į
    0.09
    çľĭè¦ĭ
    0.09
    Activations Density 0.102%

    No Known Activations