© 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. 64078
    Prev
    Next
    INDEX
    Explanations

    edema

    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
    大åݦ
    -0.09
    第ä¸ī代
    -0.08
    ÐĶÐķ
    -0.08
    å±Ī
    -0.08
    亡
    -0.08
    æł¹æį®èĩªå·±
    -0.08
    ä¸įåľ¨
    -0.08
    ÅĽÄĩ
    -0.08
    èIJ½åĪ°
    -0.08
    械
    -0.08
    POSITIVE LOGITS
    èĩĥ
    0.11
    æ°´èĤ¿
    0.11
    嵬
    0.10
    FRING
    0.10
    æĽĪ
    0.09
    orr
    0.09
    èĤ¿
    0.09
    èĨ¨
    0.09
    èĨ¨èĥĢ
    0.09
     swelling
    0.09
    Activations Density 0.258%

    No Known Activations