© 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. 6188
    Prev
    Next
    INDEX
    Explanations

    exhaust gas

    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
    åı¯éĿłçļĦ
    -0.11
    件
    -0.10
    èĩªèº«
    -0.09
    æ±Ľ
    -0.09
    å¥łåŁº
    -0.09
    åĢº
    -0.09
    oom
    -0.09
    çĶ¨èĩªå·±çļĦ
    -0.09
    以人æ°ij
    -0.09
    ends
    -0.09
    POSITIVE LOGITS
    system
    0.09
    ohl
    0.08
    ISA
    0.08
    éĿĸ
    0.08
    yte
    0.08
    ivent
    0.08
    æĶ¶éĽĨ
    0.08
     Bundy
    0.08
    iang
    0.08
     recept
    0.07
    Activations Density 0.012%

    No Known Activations