© 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. 24177
    Prev
    Next
    INDEX
    Explanations

    astrology rituals Earth Persona Magick

    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
    æĶ¸
    -0.09
     ÑĢеÑģÑĤ
    -0.09
    åĢ¾
    -0.09
     foe
    -0.09
    _ram
    -0.09
    åĤ¾
    -0.09
    榮
    -0.08
    年度
    -0.08
    .vote
    -0.08
    isd
    -0.08
    POSITIVE LOGITS
     blanks
    0.09
    éķ¿ä¸īè§Ĵ
    0.09
    DMI
    0.09
    ateria
    0.09
    é²ĩ
    0.09
    æľĢå¿«çļĦ
    0.09
    -master
    0.09
    å·¥ä½ľå®¤
    0.09
    é«ĺä»·
    0.09
     Magick
    0.08
    Activations Density 0.056%

    No Known Activations