© 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. 16559
    Prev
    Next
    INDEX
    Explanations

    performing on stage

    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
    ä¸įéĢļ
    -0.10
    çĿļ
    -0.09
    ä¸įä¿¡
    -0.09
    æ¯ĶæĪij
    -0.09
     Orr
    -0.09
    è¿IJè¡Į
    -0.09
    æ¯ĶåĪĨ
    -0.09
    .um
    -0.09
    åģľçķĻåľ¨
    -0.09
    缨
    -0.09
    POSITIVE LOGITS
    ãĤ¸ãĥ£ãĥ³
    0.10
    åij¨æģ©
    0.09
    æ¬²æľĽ
    0.09
    åĺī宾
    0.09
    è¿ĩçļĦ
    0.08
     sor
    0.08
    èľĺèĽĽ
    0.08
    rud
    0.08
    çĭ¬è§Ĵ
    0.08
    ä¸Ģ次
    0.08
    Activations Density 0.016%

    No Known Activations