© 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. 59322
    Prev
    Next
    INDEX
    Explanations

    page related 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¿Ļç§į
    -0.12
    åľ¨å¤ĸ
    -0.12
    åľ¨æѤ
    -0.11
    åľ¨ä¸Ģèµ·
    -0.11
    åľ¨ä¸Ģ个
    -0.11
    åľ¨åħ¶
    -0.10
    åľ¨ä»ĸ
    -0.10
    åľ¨è¿Ļ
    -0.10
    åľ¨å®¶
    -0.10
    åľ¨ç½ijä¸Ĭ
    -0.10
    POSITIVE LOGITS
     behalf
    0.18
    ä¹ĭä¸Ĭ
    0.11
    ä¸Ĭæľī
    0.11
    çŁ¢
    0.10
     ÙĪعÙĦÙī
    0.10
     оÑģнове
    0.09
    ä¸Ĭãģ§
    0.09
    _FUNCTIONS
    0.09
     thượng
    0.09
    ellas
    0.09
    Activations Density 0.315%

    No Known Activations