© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21919
    Prev
    Next
    INDEX
    Explanations

    you choose not regenerated

    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
    åĩłä¹İæīĢæľī
    -0.10
    éĿŀ常å¤ļçļĦ
    -0.10
    åĩłä¹İ
    -0.09
     probably
    -0.09
     zwar
    -0.09
    hiba
    -0.09
    ç¬ĶèĢħ
    -0.09
    å¦Ĥæŀľæľī
    -0.09
    çľĭäºĨçľĭ
    -0.09
    ãĥķãĥ¬
    -0.09
    POSITIVE LOGITS
    羣çļĦ
    0.12
    æľīä»»ä½ķ
    0.11
     ever
    0.10
    ä¸ĩä¸Ģ
    0.10
    avax
    0.09
    æł¹æľ¬å°±ä¸į
    0.09
    åıªæĺ¯
    0.09
     EVER
    0.09
     ×ij׼׾׾
    0.09
     otherwise
    0.09
    Activations Density 0.137%

    No Known Activations