© 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. 40294
    Prev
    Next
    INDEX
    Explanations

    waiting time duration

    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
    å¤ĦåĪĨ
    -0.11
    é²Ī
    -0.09
    Knife
    -0.09
    ç¢İ
    -0.09
     Sham
    -0.09
    aina
    -0.09
    çªģå¦Ĥåħ¶æĿ¥
    -0.09
    æĻĸ
    -0.09
    èł¡
    -0.08
    æĮŁ
    -0.08
    POSITIVE LOGITS
    æĻ¾
    0.15
    çĦĻ
    0.10
    çĥĺ
    0.10
    å¹²çĩ¥
    0.10
     drying
    0.10
    第äºĮ天
    0.10
     overnight
    0.10
     ÑģоÑħ
    0.10
    çĥĺå¹²
    0.10
    åıijéħµ
    0.09
    Activations Density 0.065%

    No Known Activations