© 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. 60651
    Prev
    Next
    INDEX
    Explanations

    time and 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
    çĶµåİĤ
    -0.10
    rus
    -0.09
    æıIJåīį
    -0.09
    ÃľN
    -0.08
    çľĭä¸įåĩº
    -0.08
    éĽ¾
    -0.08
    çĶ¨äºĨ
    -0.08
    Postal
    -0.08
    kus
    -0.08
    (fun
    -0.08
    POSITIVE LOGITS
    åĩłå¹´
    0.14
    ä¸Ģ段æŶéĹ´
    0.13
    å¤ļä¹ħ
    0.13
    åĩłå¤©
    0.13
    ä¸įä¹ħ
    0.12
    åĩłä¸ªæľĪ
    0.12
    ä¸Ģåij¨
    0.12
    å±ĬæŶ
    0.11
    两年
    0.11
    åįĬå¹´
    0.11
    Activations Density 0.024%

    No Known Activations