© 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. 7060
    Prev
    Next
    INDEX
    Explanations

    workshop or garage

    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
    ä¸įæŃ»
    -0.10
    Deaths
    -0.09
    ispers
    -0.09
    ä¸ī家
    -0.09
    ç¥Ŀç¦ı
    -0.09
    Ø´ÙĨ
    -0.09
    延
    -0.09
    _WP
    -0.09
    èµ°å¾Ĺ
    -0.09
    icient
    -0.08
    POSITIVE LOGITS
    æģ½
    0.11
    æĸ°è½¦
    0.10
    ä¸ĢåĽ¢
    0.09
    å·¥ç¨ĭæľºæ¢°
    0.09
    车éĹ´
    0.09
    å·¥åħ·
    0.09
    éĴ£
    0.09
    æĥļ
    0.09
    éĶ·
    0.09
    åľºåľ°
    0.09
    Activations Density 0.066%

    No Known Activations