© 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. 6876
    Prev
    Next
    INDEX
    Explanations

    critical condition

    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
    å½¹
    -0.10
    ä»ħ次äºİ
    -0.10
    æĿ¥ä¸įåıĬ
    -0.09
    åĸĩåıŃ
    -0.09
    çªĿ
    -0.09
    å¦Ĥä½ķçľĭå¾ħ
    -0.09
    ç»ĪçĶŁ
    -0.09
    å¼ĢåĬŀ
    -0.09
    udi
    -0.08
     Wahl
    -0.08
    POSITIVE LOGITS
    åį±
    0.13
    çĹħæĥħ
    0.13
    çĬ¶åĨµ
    0.10
     ìĥģíĥľ
    0.10
    çĬ¶æĢģ
    0.09
    çĽijæĬ¤
    0.09
    cakes
    0.09
    çĽijè§Ĩ
    0.09
    å®ļçĤ¹
    0.09
    æıı
    0.09
    Activations Density 0.080%

    No Known Activations