© 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. 29604
    Prev
    Next
    INDEX
    Explanations

    direction or position

    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
    çķĻå®Ī
    -0.11
    å¹Ħ
    -0.10
    lug
    -0.10
    гон
    -0.10
    çģµæĦŁ
    -0.09
    åĩłåı¥
    -0.09
    å°¤åħ¶æĺ¯åľ¨
    -0.09
    kop
    -0.08
    gow
    -0.08
    __,__
    -0.08
    POSITIVE LOGITS
    åħij
    0.09
    çļĦåľ°
    0.09
    æı©
    0.09
    éĸĵéģķãģĦ
    0.09
     Commerce
    0.09
    å°±åºĶ该
    0.08
    ä¸Ĭå²Ĺ
    0.08
    èµĦæ·±
    0.08
     onCreateView
    0.08
    没æľī太大
    0.08
    Activations Density 0.061%

    No Known Activations