© 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. 52476
    Prev
    Next
    INDEX
    Explanations

    feel free to ask or comment

    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
    å·®ä¸įå¤ļ
    -0.10
    äºĨ好å¤ļ
    -0.09
    æĢİä¹ĪåĬŀ
    -0.09
    æĿľåħ°
    -0.09
    鸱
    -0.09
    çĢĽ
    -0.09
    appe
    -0.09
    å¾µ
    -0.09
     долж
    -0.09
    å·®çĤ¹
    -0.09
    POSITIVE LOGITS
    ä»»ä½ķ
    0.13
    ä»»ä½ķå½¢å¼ı
    0.12
     any
    0.12
    ä»»ä½ķ人
    0.11
    Anywhere
    0.11
    ä»»ä½ķä¸Ģ个
    0.10
    ä»»ä½ķæŶåĢĻ
    0.10
    æľīä»»ä½ķ
    0.10
     anywhere
    0.10
    _any
    0.10
    Activations Density 0.021%

    No Known Activations