© 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. 895
    Prev
    Next
    INDEX
    Explanations

    award winners and prizes

    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
    åıĹå½±åĵį
    -0.09
    å¥Ĺè£ħ
    -0.09
     Deluxe
    -0.08
     Mane
    -0.08
    åºĦæĿij
    -0.08
    æĺ¯åĽ½åĨħ
    -0.08
    \Helper
    -0.08
    _TM
    -0.08
    æī¿åıĹ
    -0.08
    æģ¯æģ¯
    -0.08
    POSITIVE LOGITS
    å¥ĸ
    0.13
    çļĦæľĢä½³
    0.12
    æľĢä½³
    0.12
    年度
    0.12
    çŃīå¥ĸ
    0.11
    æİĪäºĪ
    0.11
    æ®Ĭ
    0.10
    çł´
    0.10
     Award
    0.10
     award
    0.10
    Activations Density 0.134%

    No Known Activations