© 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. 29597
    Prev
    Next
    INDEX
    Explanations

    and clauses

    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
    æ£ł
    -0.11
    彪
    -0.10
    VERIFY
    -0.10
    çļĦåĪ©çĽĬ
    -0.10
    leases
    -0.10
    ç½ijç«Ļåľ°åĽ¾
    -0.09
    ãģ¨ãģ«ãģĭãģı
    -0.09
    妥
    -0.09
    大ä¼ļä¸Ĭ
    -0.09
    ä¸įä½Ĩ
    -0.09
    POSITIVE LOGITS
    æľīçļĦ
    0.08
    .setHorizontal
    0.08
    åĢŁçĶ¨
    0.08
    åŃĹ
    0.07
    æľīä¸Ģ
    0.07
    setattr
    0.07
    å±ij
    0.07
     gross
    0.07
    urge
    0.07
    gross
    0.07
    Activations Density 0.027%

    No Known Activations