© 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. 24058
    Prev
    Next
    INDEX
    Explanations

    however

    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
     almost
    -0.09
    åĩłä¹İ没æľī
    -0.08
    åĩłä¹İ
    -0.08
    å¹¾ä¹İ
    -0.08
    almost
    -0.08
     поÑĩÑĤи
    -0.08
     br
    -0.07
    kind
    -0.07
     "...
    -0.07
     Ben
    -0.07
    POSITIVE LOGITS
     however
    0.35
    åį´
    0.29
    however
    0.28
    åį´æĺ¯
    0.27
    çĦ¶èĢĮ
    0.27
     jedoch
    0.27
     же
    0.26
     однако
    0.25
    åį»
    0.25
     porém
    0.25
    Activations Density 0.451%

    No Known Activations