© 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. 12115
    Prev
    Next
    INDEX
    Explanations

    feature branch

    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
    å¿«æį·
    -0.10
     Prov
    -0.10
    æĪIJçĨŁ
    -0.09
    俦
    -0.09
    åĩij
    -0.09
    寻
    -0.09
    ãĥ«ãĥī
    -0.09
    éĶ´
    -0.09
    äºĮæīĭ
    -0.09
    INE
    -0.09
    POSITIVE LOGITS
     ga
    0.09
    æ³³
    0.09
    è¹¼
    0.09
    æīijåħĭ
    0.08
    ç¼ĸåĪ¶
    0.08
    æ³£
    0.08
    ::__
    0.08
    ç¾Ŀ
    0.08
    éĩįçĤ¹é¡¹çĽ®
    0.08
    çĹĶ
    0.08
    Activations Density 0.101%

    No Known Activations