© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 10208
    Prev
    Next
    INDEX
    Explanations

    also, followed by a verb or 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
    ersed
    -0.09
    æĽ´å¤ļçļĦ
    -0.09
    åĨįä¸Ģ次
    -0.09
    ä¸Ģ次次
    -0.09
    ä¸įä»ħåı¯ä»¥
    -0.08
    ëĭĪê¹Į
    -0.08
    éĢĨ
    -0.08
    åį³ä¾¿
    -0.08
    æĺ¯çĶ¨æĿ¥
    -0.08
    REATE
    -0.08
    POSITIVE LOGITS
    åıijæĮ¥ä½ľçĶ¨
    0.12
    è¿ĩæĿ¥
    0.09
    åıĹåĪ°å½±åĵį
    0.09
    anes
    0.08
    ory
    0.08
    éĿŀ常éĩįè¦ģ
    0.08
    åĩºè·¯
    0.08
    èĩªæѤ
    0.08
    åĢ¼å¾Ĺåħ³æ³¨
    0.08
    åŃĺåľ¨ä¸Ģå®ļ
    0.08
    Activations Density 0.044%

    No Known Activations