© 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. 4912
    Prev
    Next
    INDEX
    Explanations

    using one or two hands

    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
    ullo
    -0.10
    å½ĵæĹ¥
    -0.10
    èĨı
    -0.09
    æ¢Ń
    -0.09
    éĢł
    -0.09
    æľĹ
    -0.09
    æľĢåIJİä¸Ģ次
    -0.09
    å±ķ
    -0.08
    achel
    -0.08
     cục
    -0.08
    POSITIVE LOGITS
    ä¸Ģåıªæīĭ
    0.17
    åı³æīĭ
    0.15
    å·¦æīĭ
    0.14
     hand
    0.13
    æīĭéĩĮ
    0.13
     ÑĢÑĥк
    0.13
    åıĮæīĭ
    0.12
    两æīĭ
    0.12
    ä¸Ģæīĭ
    0.12
    æīĭ
    0.12
    Activations Density 0.072%

    No Known Activations