© 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. 18083
    Prev
    Next
    INDEX
    Explanations

    saying that

    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
    à¹ģà¸ģ
    -0.09
    à¹ģ
    -0.08
    æĸĹ
    -0.08
    acking
    -0.08
    -topic
    -0.08
    à¹Ĥà¸Ī
    -0.08
    ila
    -0.08
    ç¡®
    -0.08
    éĢĹ
    -0.08
    æĭ¿
    -0.08
    POSITIVE LOGITS
    说èĩªå·±
    0.12
    ä¸Ģåı¥è¯Ŀ
    0.10
    è¯Ńæ°Ķ
    0.10
    æĪij说
    0.10
    æݩ饰
    0.10
     antagon
    0.10
    大家åı¯ä»¥
    0.09
    åŃ°
    0.09
    说
    0.09
    è·³åĩº
    0.09
    Activations Density 0.028%

    No Known Activations