© 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. 12278
    Prev
    Next
    INDEX
    Explanations

    questions and uncertainty

    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
    åĭĥ
    -0.09
    ä¸į妨
    -0.09
    认è¯ĨåĪ°
    -0.09
    æī¿è®¤
    -0.08
    讲è¯Ŀ
    -0.08
    注æĦıåĪ°
    -0.08
    isle
    -0.08
    ilated
    -0.08
    cene
    -0.08
    设计æĸ¹æ¡Ī
    -0.08
    POSITIVE LOGITS
    æľªçŁ¥
    0.20
    ä¸įç¡®å®ļ
    0.17
    ä¸įç¡®å®ļæĢ§
    0.16
     unknown
    0.14
     uncertain
    0.13
    Unknown
    0.13
    ä¸įæ¸ħæ¥ļ
    0.13
     Unknown
    0.12
    _unknown
    0.12
     uncertainty
    0.12
    Activations Density 0.041%

    No Known Activations