© 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. 16881
    Prev
    Next
    INDEX
    Explanations

    immediate, instant, now, same-day

    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
    æłĩåĩĨåĮĸ
    -0.09
    캡
    -0.09
    доÑĢ
    -0.09
    éĻĮ
    -0.09
    ycz
    -0.08
    crew
    -0.08
    åºĦ
    -0.08
    WithContext
    -0.08
    äºĨä¸Ģ份
    -0.08
    è¶ĬæĿ¥è¶Ĭ大
    -0.08
    POSITIVE LOGITS
     immedi
    0.22
     immediate
    0.22
    ç«ĭåį³
    0.21
    ç«ĭåĪ»
    0.20
    åį³æŶ
    0.19
     Immediate
    0.19
    Immediate
    0.18
    马ä¸Ĭ
    0.17
     immediately
    0.16
    ç«ĭ马
    0.16
    Activations Density 0.094%

    No Known Activations