© 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. 47633
    Prev
    Next
    INDEX
    Explanations

    world's or of the

    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
    çļĦéĩįè¦ģ
    -0.09
    é¦ĸéĢī
    -0.09
     oldest
    -0.09
    uft
    -0.08
     earliest
    -0.08
    管çIJĨåĴĮ
    -0.08
    çŁ³
    -0.08
    odi
    -0.08
    çĿ¹
    -0.08
    åĶ¯æľī
    -0.08
    POSITIVE LOGITS
    åĨħåľ°
    0.10
    arium
    0.10
    è°ª
    0.09
    åįİ润
    0.09
    rä
    0.08
    idos
    0.08
    xEF
    0.08
    кÑģ
    0.08
    磫
    0.08
    å½ĵä»Ĭ
    0.08
    Activations Density 0.139%

    No Known Activations