© 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. 2830
    Prev
    Next
    INDEX
    Explanations

    self-representation or self-activation

    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
    æļ´
    -0.12
    çĪĨ
    -0.09
    å·¡åĽŀ
    -0.09
    æīĺ
    -0.09
    æīĺ管
    -0.09
    æĺĻ
    -0.09
    åīįæīĢ
    -0.09
    彪
    -0.08
    éĢĢ
    -0.08
     eBook
    -0.08
    POSITIVE LOGITS
    为èĩªå·±
    0.16
    ç»Ļèĩªå·±
    0.16
    对èĩªå·±
    0.15
    èĩªèº«
    0.15
    èĩªæĪij
    0.14
    self
    0.14
    对èĩªå·±çļĦ
    0.14
    èĩªå¸¦
    0.14
    èĩªè¡Į
    0.14
     self
    0.14
    Activations Density 0.270%

    No Known Activations