© 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. 16785
    Prev
    Next
    INDEX
    Explanations

    pain

    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
    wor
    -0.10
    IFT
    -0.10
    客æľį
    -0.09
     Pharmaceuticals
    -0.09
    tl
    -0.09
    coach
    -0.09
     churn
    -0.09
    车éĺŁ
    -0.09
    çľīæ¯Ľ
    -0.08
     america
    -0.08
    POSITIVE LOGITS
    lessly
    0.10
    licable
    0.09
    èĬĴ
    0.09
    æīª
    0.08
    ful
    0.08
    éĻĽ
    0.08
    ensitive
    0.08
     RAND
    0.08
    CHIP
    0.08
    staking
    0.08
    Activations Density 0.073%

    No Known Activations