© 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. 47453
    Prev
    Next
    INDEX
    Explanations

    make your own

    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
    oretical
    -0.09
    æĪij个人
    -0.09
    æľ¬èº«
    -0.08
     Bloom
    -0.08
    yahoo
    -0.08
    ursed
    -0.08
    ACHER
    -0.08
    uzzi
    -0.08
    æĪijèĩªå·±
    -0.08
     crest
    -0.08
    POSITIVE LOGITS
    æļĹæļĹ
    0.10
    åĿ¦
    0.10
    æľĭ
    0.10
     Honest
    0.09
    irty
    0.09
    iable
    0.09
    弥补
    0.09
    并éĢļè¿ĩ
    0.09
    æĻ°
    0.09
    并ä¸İ
    0.09
    Activations Density 0.019%

    No Known Activations