© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 48870
    Prev
    Next
    INDEX
    Explanations

    nothing found

    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
    Not in Any Lists

    No Comments

    Negative Logits
    åħħåĪĨåĪ©çĶ¨
    -0.10
    åı¬
    -0.08
    lest
    -0.08
    éĻIJåĪ¶
    -0.08
    è½²
    -0.08
    DEX
    -0.08
    ivol
    -0.08
    åIJĮæĹ¶ä¹Łæĺ¯
    -0.08
     consenting
    -0.08
    åĩĽ
    -0.08
    POSITIVE LOGITS
    ä¸Ŀ毫
    0.12
    æľīä»»ä½ķ
    0.11
    踪
    0.11
    çľĭä¸įè§ģ
    0.11
    身影
    0.10
    ä¸įè§ģ
    0.10
    ãģĦãģŁãģł
    0.10
     Äijâu
    0.10
    ä»»ä½ķå½¢å¼ı
    0.09
    ä¹Łæ²¡æľī
    0.09
    Activations Density 0.101%

    No Known Activations