© 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. 3538
    Prev
    Next
    INDEX
    Explanations

    describing elements and their properties

    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
    ä¸Ģçŀ¬éĹ´
    -0.11
    强大
    -0.10
    åIJĮæĹ¶ä¹Łæĺ¯
    -0.10
    ä¸įåIJĮäºİ
    -0.10
     zwar
    -0.09
    ä¹Łæĺ¯ä¸Ģ个
    -0.09
    è±ķ
    -0.09
    类产åĵģ
    -0.09
    åīįæīĢæľªæľī
    -0.09
    åIJĮæĹ¶ä¹Ł
    -0.09
    POSITIVE LOGITS
    åħ¶å®ĥ
    0.12
    åħ¶ä»ĸçļĦ
    0.12
     ones
    0.11
    ãģĿãģĨãģ§
    0.11
    å¹²èĦĨ
    0.11
    åı¦è¡Į
    0.10
    äºĮèĢħ
    0.10
    åħ¶ä»ĸ
    0.10
    缸åıį
    0.10
     outright
    0.10
    Activations Density 0.402%

    No Known Activations