© 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. 21586
    Prev
    Next
    INDEX
    Explanations

    voiceover or narration

    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
    éĢĢè¿ĺ
    -0.10
    è¢ĸ
    -0.10
    ä¸Ĭä¸ĭ游
    -0.10
     Slee
    -0.09
    æ¶Ŀ
    -0.09
    æ³
    -0.09
    inks
    -0.09
    人èĦī
    -0.09
    éĿ¢åŃIJ
    -0.09
    å¹³
    -0.08
    POSITIVE LOGITS
    解说
    0.14
    éħįéŁ³
    0.13
     narration
    0.11
     commentary
    0.11
    Narr
    0.11
     narr
    0.11
    éħį
    0.10
    æĹģ
    0.10
     Dub
    0.10
     miá»ĩng
    0.09
    Activations Density 0.094%

    No Known Activations