© 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. 59375
    Prev
    Next
    INDEX
    Explanations

    eliners, planista, emark, eturn

    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
    ein
    -0.10
    ãģĬãĤĬ
    -0.10
    eos
    -0.09
    ãĥ¼ãĤ·ãĥ§ãĥ³
    -0.09
    iculty
    -0.09
    eer
    -0.08
     Terry
    -0.08
    å½ķçĶ¨
    -0.08
    ei
    -0.08
    eval
    -0.08
    POSITIVE LOGITS
    ##_
    0.11
    à¹Į
    0.11
    emark
    0.11
    emarks
    0.10
    eload
    0.10
    ewise
    0.10
    eman
    0.10
    emax
    0.10
    ê¹IJ
    0.10
    eturn
    0.09
    Activations Density 0.487%

    No Known Activations