© 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. 2485
    Prev
    Next
    INDEX
    Explanations

    microphone or recording

    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
    çľ¼ç§ij
    -0.11
    å¿«æĬ¥
    -0.10
    æ¸ħæ°´
    -0.09
    æĹ¥æľ¬ãģ®
    -0.09
    çĪ·
    -0.09
    æµĥ
    -0.09
    æĢ¥
    -0.09
    anel
    -0.09
    åĬłåī§
    -0.08
    çļĦçľ¼
    -0.08
    POSITIVE LOGITS
     microphone
    0.14
    麦åħĭ
    0.14
    å½ķ
    0.12
    å½ķåĪ¶
    0.11
    éĮĦ
    0.11
    å½ķéŁ³
    0.11
     recording
    0.10
    ðŁİ¤
    0.10
    Recording
    0.10
    æİĪ
    0.10
    Activations Density 0.087%

    No Known Activations