© 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. 40052
    Prev
    Next
    INDEX
    Explanations

    feedback and suggestions

    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
    æĪİ
    -0.11
    åĬłä¸Ĭ
    -0.09
    arton
    -0.09
    arter
    -0.08
    ingu
    -0.08
    _modifier
    -0.08
     обоÑĢ
    -0.08
    宣è¨Ģ
    -0.08
    æĽ
    -0.08
    è¶Ĭæĺ¯
    -0.08
    POSITIVE LOGITS
    åıįé¦Ī
    0.23
     feedback
    0.22
     Feedback
    0.20
    feedback
    0.19
    Feedback
    0.19
    æĦıè§ģåıįé¦Ī
    0.17
    -feedback
    0.17
    _feedback
    0.17
    .feedback
    0.16
    æĦıè§ģ
    0.15
    Activations Density 0.064%

    No Known Activations