© 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. 18696
    Prev
    Next
    INDEX
    Explanations

    topics include

    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
    è¿Ļæĺ¯æĪij们
    -0.10
    å¾Īéķ¿æŶéĹ´
    -0.10
    ä¸į失
    -0.10
    è¿Ļæĺ¯æĪij
    -0.09
    èĢģåħµ
    -0.09
    å¾Īä¹ħ
    -0.09
    èĢģçīĮ
    -0.09
    许ä¹ħ
    -0.09
     должно
    -0.09
    æľĢåIJİä¸Ģ次
    -0.09
    POSITIVE LOGITS
     include
    0.17
     includes
    0.17
    è¿ĺåĮħæĭ¬
    0.15
    主è¦ģåĮħæĭ¬
    0.14
    主è¦ģæľī
    0.14
     Include
    0.13
    ä¾Ŀ次
    0.13
    includes
    0.13
     Includes
    0.13
    åĪĨåĪ«æĺ¯
    0.13
    Activations Density 0.233%

    No Known Activations