© 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. 26152
    Prev
    Next
    INDEX
    Explanations

    funding, costs, and budget

    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
    åĿ¯
    -0.09
    å§ĭäºİ
    -0.09
    ä¸įè¿ľ
    -0.08
    åŃIJåħ¬åı¸
    -0.08
    解æĶ¾
    -0.08
    å§ĭ
    -0.08
     subsystem
    -0.08
     Äijá
    -0.08
    argon
    -0.08
    åĤ¬çĶŁ
    -0.08
    POSITIVE LOGITS
    è¿IJ转
    0.14
    æĶ¶æĶ¯
    0.13
    ç»ıè´¹
    0.13
    éĿł
    0.11
    çIJĨäºĭéķ¿
    0.11
    è¿IJèIJ¥
    0.11
    æĶ¶åĪ°
    0.10
    åĬŀåѦ
    0.10
    æİ¥åĪ°
    0.10
    åıijå±ķ壮大
    0.10
    Activations Density 0.046%

    No Known Activations