© 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. 40088
    Prev
    Next
    INDEX
    Explanations

    and then this

    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
    åħ¶ä»ĸçļĦ
    -0.13
    éĤ£å°±
    -0.12
    åĪĨæł¡
    -0.12
    åħ¶ä»ĸåĽ½å®¶
    -0.11
    åĽłä¸ºä»ĸ们
    -0.10
    æĽ´ä½ķåĨµ
    -0.10
    åįģåŃĹ
    -0.10
    éĤ£ä½ł
    -0.10
    åĽłä¸ºå®ĥ
    -0.09
    ULK
    -0.09
    POSITIVE LOGITS
    æŶåħī
    0.08
    there
    0.08
    ä¹ı
    0.08
    it
    0.08
    nder
    0.08
     Parliamentary
    0.08
    ipl
    0.07
    ä¸ĭéĿ¢æĺ¯
    0.07
    大èĩ´
    0.07
    åĪ°å¤Ħ
    0.07
    Activations Density 0.169%

    No Known Activations