© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 26468
    Prev
    Next
    INDEX
    Explanations

    Drupal, Joomla, Magento

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ç»İ
    -0.11
    elle
    -0.09
    å®ŀåľ¨
    -0.09
    åįĥä¸ĩä¸įè¦ģ
    -0.09
    ä¸įèĪį
    -0.09
    vation
    -0.09
    å¼Ģåħ·
    -0.09
    vey
    -0.08
    aptcha
    -0.08
    iert
    -0.08
    POSITIVE LOGITS
    çĶŁåŃĺ
    0.09
    erate
    0.09
    ستاÙĨ
    0.09
     sÆ°
    0.09
    icious
    0.09
    loating
    0.08
    å±IJ
    0.08
    (fi
    0.08
    cobra
    0.08
    baugh
    0.08
    Activations Density 0.043%

    No Known Activations