© 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. 24250
    Prev
    Next
    INDEX
    Explanations

    Central followed by regions

    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
    åī²
    -0.09
    æļ®
    -0.09
    è§ĴèIJ½
    -0.09
    åģ¥åº·åıijå±ķ
    -0.09
    able
    -0.09
    ạm
    -0.09
    躬
    -0.09
    åIJĪæł¼
    -0.08
    åĭ¤å¥ĭ
    -0.08
    æľīèĥ½åĬĽ
    -0.08
    POSITIVE LOGITS
    izer
    0.12
    åĬ¿
    0.10
     PURPOSE
    0.09
    éĺ²çģ«
    0.09
    éºĴ
    0.09
    åĭ¢
    0.08
    ymb
    0.08
    alerts
    0.08
    ä¼Ļä¼´åħ³ç³»
    0.08
    IZER
    0.08
    Activations Density 0.161%

    No Known Activations