© 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. 6199
    Prev
    Next
    INDEX
    Explanations

    enough or insufficient amounts

    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
    表çݰ为
    -0.09
    aign
    -0.09
     Beer
    -0.09
    Beer
    -0.09
    Ñīе
    -0.09
    延
    -0.08
    åıĻ
    -0.08
    tsx
    -0.08
    ÑijÑĢ
    -0.08
    åĪ«
    -0.08
    POSITIVE LOGITS
    è¶³å¤ŁçļĦ
    0.28
    è¶³å¤Ł
    0.25
     enough
    0.24
     sufficient
    0.18
    åħħ足çļĦ
    0.17
     Enough
    0.17
     Äijủ
    0.17
    Enough
    0.17
    å¤ł
    0.16
    æľīè¶³å¤ŁçļĦ
    0.16
    Activations Density 0.043%

    No Known Activations