© 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. 3051
    Prev
    Next
    INDEX
    Explanations

    Lewis Johnson Wind Douglas Java

    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
    寰
    -0.09
    ç«ĭä½ĵ
    -0.09
     U
    -0.08
    s
    -0.08
    heed
    -0.08
    åĶ¤
    -0.08
    ä¸ŃåĽ½éĺŁ
    -0.08
    èµ°
    -0.08
    å¸Ń
    -0.08
    éĺħ
    -0.08
    POSITIVE LOGITS
    бÑĥÑĢ
    0.12
    ä¸Ģ大æĹ©
    0.10
    ä¸ĭä¸Ģ代
    0.10
    æĸ¤
    0.10
    ëĬIJ
    0.09
     ÅŁeyler
    0.09
    ä¸ī天
    0.09
    ç¼ĸåĪ¶
    0.09
    imar
    0.09
    å¾Īæĥ³
    0.09
    Activations Density 0.013%

    No Known Activations