© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 29605
    Prev
    Next
    INDEX
    Explanations

    anticipated or -awaited

    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
    Negative Logits
    und
    -0.09
    uh
    -0.09
    éĥ½åºĶ该
    -0.08
    uts
    -0.08
    sts
    -0.08
    梦è§ģ
    -0.08
    uvo
    -0.08
    ç»ıæŁ¥
    -0.08
    åĵĪå°Ķ
    -0.08
    weg
    -0.08
    POSITIVE LOGITS
    æĿ¥ä¸´
    0.11
    å·²ä¹ħ
    0.11
    å·²ä¹ħçļĦ
    0.11
    çļĦåĪ°æĿ¥
    0.10
    å¤ļ人
    0.09
    ä¸ļåĨħ
    0.09
    èĩªæĿ¥
    0.08
    ä¹ĭä½ľ
    0.08
    å½ĴæĿ¥
    0.08
    åį´æĺ¯
    0.08
    Activations Density 0.008%

    No Known Activations