© 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. 30232
    Prev
    Next
    INDEX
    Explanations

    month names and dates

    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
    æĤ¬
    -0.09
    åIJĮç±»
    -0.09
    çĶ¸
    -0.09
     ÑĩÑĥÑĤÑĮ
    -0.09
    åIJĮä»ģ
    -0.09
    çīºçī²
    -0.08
     MQ
    -0.08
     ÑģоÑħÑĢани
    -0.08
    пиÑĤ
    -0.08
    ceb
    -0.08
    POSITIVE LOGITS
    æ£Ģ
    0.11
    ä¸ĢçĤ¹ä¹Łä¸į
    0.10
    深度èŀįåIJĪ
    0.09
    icho
    0.09
    çĹķ
    0.08
    æ·±åħ¥å¼Ģå±ķ
    0.08
    æĪij们ä¸Ģèµ·
    0.08
    äºĨèµ·æĿ¥
    0.08
    ä¸¥æł¼èIJ½å®ŀ
    0.08
    ä¸Ģå¼ł
    0.08
    Activations Density 0.287%

    No Known Activations