© 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. 22627
    Prev
    Next
    INDEX
    Explanations

    very [positive adjective]

    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
    ä¸įåı¯ä»¥
    -0.11
    æŀ¯çĩ¥
    -0.09
    ç¡®
    -0.09
    åĢŁåı£
    -0.09
    ä¸įæĺ¯å¾Ī
    -0.08
    åı£åı·
    -0.08
    å°ijéĩı
    -0.08
    æīįåı¯ä»¥
    -0.08
    åĩºçĤī
    -0.08
    空çĻ½
    -0.08
    POSITIVE LOGITS
     á»ķn
    0.09
    稳å®ļ
    0.09
    ä¸įéĶĻ
    0.09
    幸ç¦ı
    0.09
    åģĪ
    0.09
    æĭ¥æĬ¤
    0.08
    æĭ¿
    0.08
    çľ¼çIJĥ
    0.08
    èĪĴå¿ĥ
    0.08
    æĶ¾åľ¨
    0.08
    Activations Density 0.034%

    No Known Activations