© 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. 29820
    Prev
    Next
    INDEX
    Explanations

    in terms of

    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
    ç»ĵå±Ģ
    -0.10
    ä¸įæĸŃå®ĮåĸĦ
    -0.09
    ä¹ĭéģĵ
    -0.09
    å¿Ļ
    -0.09
    ä¸ĩéĩĮ
    -0.08
    ä¹ĭä½ľ
    -0.08
    ä¸Ģ页
    -0.08
    äºĮåŃĹ
    -0.08
    åįĥéĩĮ
    -0.08
    ì¶ĺ
    -0.08
    POSITIVE LOGITS
     strength
    0.12
    è´¨éĩıåĴĮ
    0.11
    稳å®ļæĢ§
    0.11
    æķĪçİĩ
    0.11
     both
    0.10
    åĩĨç¡®æĢ§
    0.10
     size
    0.10
    强度
    0.10
    çľ¼çķĮ
    0.10
    åIJĦæĸ¹éĿ¢
    0.10
    Activations Density 0.087%

    No Known Activations