© 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. 846
    Prev
    Next
    INDEX
    Explanations

    my experienced difficulties

    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
    æİ¥è¿ĩ
    -0.09
    éĹ®åĢĻ
    -0.09
    ä¸Ģçľĭ
    -0.09
    é»ĺé»ĺåľ°
    -0.09
    åIJį人
    -0.09
    æ¡ĥ
    -0.09
    çĸijä¼¼
    -0.09
    nip
    -0.09
    åºĶæľīçļĦ
    -0.09
    æī¶
    -0.08
    POSITIVE LOGITS
    çģµæĦŁ
    0.11
     originals
    0.10
    åĪ¶ä½ľ
    0.10
    åĨĻçļĦ
    0.09
    欢è¿İ大家
    0.09
    Ñĥнк
    0.09
    /loader
    0.09
    åĶ®
    0.09
    èĢĹè´¹
    0.09
    åĨł
    0.08
    Activations Density 0.305%

    No Known Activations