© 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. 40258
    Prev
    Next
    INDEX
    Explanations

    broken package, fault, defects

    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
    roscope
    -0.09
     SC
    -0.09
    çĶŁæķĪ
    -0.09
    åľī
    -0.08
    uri
    -0.08
    ä¼ģ
    -0.08
     bli
    -0.08
    DIST
    -0.08
    _gui
    -0.08
    2
    -0.08
    POSITIVE LOGITS
    缺
    0.10
    riad
    0.09
    è´¨éĩıéĹ®é¢ĺ
    0.09
    å¼Ĥè®®
    0.09
     facult
    0.09
    anky
    0.09
    æķ·
    0.09
     ë°ľìĥĿ
    0.09
    éħįéĢģ
    0.09
    æİĢ
    0.09
    Activations Density 0.011%

    No Known Activations