© 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. 47534
    Prev
    Next
    INDEX
    Explanations

    award ceremonies and prizes

    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
    åħ¥ä¾µ
    -0.09
    .prot
    -0.09
    atel
    -0.08
    å»ºåĽ½
    -0.08
    Bug
    -0.08
    osto
    -0.08
    åĩºæ±Ĺ
    -0.08
    è¿ĺæľī
    -0.08
    esthes
    -0.08
    åĨħè¡£
    -0.08
    POSITIVE LOGITS
    å¥ĸ项
    0.23
    é¢ģå¥ĸ
    0.22
     award
    0.20
     awards
    0.18
    å¥ĸ
    0.18
    å¥ĸåĬ±
    0.16
    èİ·å¥ĸ
    0.15
     Award
    0.15
    çŃīå¥ĸ
    0.14
     awarded
    0.14
    Activations Density 0.132%

    No Known Activations