© 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. 24197
    Prev
    Next
    INDEX
    Explanations

    resource management branch chief

    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
    ç»ĨèĬĤ
    -0.09
    .xlim
    -0.09
    æºĸ
    -0.09
    æĪĺçķ¥å¸ĥå±Ģ
    -0.08
    åĩĨæŶ
    -0.08
    ÑĢож
    -0.08
     >>↵↵
    -0.08
    å®īçĦ¶
    -0.08
    渡
    -0.08
    æĤ¬å´ĸ
    -0.08
    POSITIVE LOGITS
    éĢł
    0.10
     advoc
    0.09
    oden
    0.09
    ä¸İåħ¶
    0.09
    æ¯ıåij¨
    0.08
    两级
    0.08
    åľºåľ°
    0.08
    没æľīå¿ħè¦ģ
    0.08
    urma
    0.08
    æī¿åĬŀ
    0.08
    Activations Density 0.331%

    No Known Activations