© 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. 29493
    Prev
    Next
    INDEX
    Explanations

    percent signs or words

    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
    åľ¨è¿ĩ渡
    -0.09
    ä¸įå¤ļ
    -0.09
    æµį
    -0.08
     Lane
    -0.08
     lane
    -0.08
    Ñģоб
    -0.08
    Destination
    -0.08
    ä¸įèī¯ä¿¡æģ¯
    -0.08
    Õ¹
    -0.08
    CELL
    -0.08
    POSITIVE LOGITS
    éŀł
    0.08
    è´§
    0.08
    콤
    0.08
    大湾åĮº
    0.08
    æİĮ
    0.08
    éĿ©
    0.08
    äºĮæĪĺ
    0.08
    _transient
    0.08
    opal
    0.08
    yyy
    0.08
    Activations Density 0.082%

    No Known Activations