© 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. 58235
    Prev
    Next
    INDEX
    Explanations

    years ago

    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
     recent
    -0.11
    ä»İåݻ年
    -0.10
    History
    -0.10
    è¿ijæľŁ
    -0.09
     histories
    -0.09
    忽
    -0.09
    è¿ijäºĽ
    -0.09
     History
    -0.09
     Recent
    -0.09
     history
    -0.09
    POSITIVE LOGITS
    éĤ£æŶ
    0.24
    å½ĵæŶçļĦ
    0.23
    å½ĵæŶ
    0.22
    éĤ£æŶåĢĻ
    0.21
    éĤ£ä¸ªæŶåĢĻ
    0.21
    çķ¶æĻĤ
    0.19
     ëĭ¹ìĭľ
    0.19
    å½¼
    0.16
    æĪijå½ĵæŶ
    0.13
    å½ĵå¹´
    0.11
    Activations Density 0.133%

    No Known Activations