© 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. 4503
    Prev
    Next
    INDEX
    Explanations

    audio file handling

    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
    秩
    -0.10
     videot
    -0.10
    çļĦ缮åħī
    -0.10
    å½ķåĥı
    -0.09
    çĶµè§Ĩ
    -0.09
     filming
    -0.09
    çļĦçľ¼åħī
    -0.09
     filmed
    -0.09
     televised
    -0.08
     tv
    -0.08
    POSITIVE LOGITS
    èĢ³è¾¹
    0.12
    åIJ¬å®Į
    0.11
    èĢ³
    0.11
     ear
    0.10
    åIJ¬åIJ¬
    0.10
    ä¸ĢåIJ¬
    0.10
    åIJ¬è¿ĩ
    0.10
    åIJ¬å¾Ĺ
    0.10
    åIJ¬
    0.10
    èĢ³æľµ
    0.10
    Activations Density 0.070%

    No Known Activations