© 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. 59169
    Prev
    Next
    INDEX
    Explanations

    thanks for

    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
    åĩĨ
    -0.10
    çı©
    -0.10
    iação
    -0.09
    泪
    -0.08
    ели
    -0.08
    水产
    -0.08
    <KeyValuePair
    -0.08
    í
    -0.08
    ä¸Ģçľ¼
    -0.08
    uteur
    -0.08
    POSITIVE LOGITS
    谢谢
    0.11
    è°¢è°¢ä½ł
    0.09
    åĽĽå¤§
    0.08
    çĦĬ
    0.08
     thank
    0.08
    èĪĴæľį
    0.08
    è¿Ľå±ķ
    0.08
    æĻ¨
    0.08
    ç¥ł
    0.08
     inference
    0.08
    Activations Density 0.013%

    No Known Activations