© 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. 24256
    Prev
    Next
    INDEX
    Explanations

    "why" question starters

    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
     EntryPoint
    -0.09
     gent
    -0.09
    erna
    -0.09
    ä¸įåģľçļĦ
    -0.08
    åħ¸åŀĭ
    -0.08
    .inline
    -0.08
    éĿŀ常çļĦ
    -0.08
     Lindsey
    -0.08
    碰
    -0.08
    åľºéĿ¢
    -0.08
    POSITIVE LOGITS
    为ä»Ģä¹Īä¸į
    0.13
    亲èĩª
    0.10
    ä¸įæĿ¥
    0.10
    ä¸į大
    0.10
    大èĥĨ
    0.10
    为ä»Ģä¹Ī
    0.09
    ä½ķå¿ħ
    0.09
    ales
    0.09
    rawler
    0.09
    躬
    0.09
    Activations Density 0.014%

    No Known Activations