© 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. 6301
    Prev
    Next
    INDEX
    Explanations

    depend on / rely on

    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
    .za
    -0.09
    åĨĻçĿĢ
    -0.09
    æĿĤ
    -0.08
    èĶ¼
    -0.08
    é¤IJæ¡Į
    -0.08
     \/
    -0.08
    æīĢ以æĪij们
    -0.08
    çļĦ缮çļĦ
    -0.08
    纪å½ķ
    -0.08
    裹
    -0.08
    POSITIVE LOGITS
    ä¾ĿéĿł
    0.15
    ä¾Ŀèµĸ
    0.15
    åĢļ
    0.13
     relied
    0.13
     rely
    0.13
     reliance
    0.12
     reliant
    0.12
    ä¾Ŀæīĺ
    0.12
    åĩŃ
    0.12
     relies
    0.12
    Activations Density 0.055%

    No Known Activations