© 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. 60778
    Prev
    Next
    INDEX
    Explanations

    website or site

    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
    åĩĨæŶ
    -0.11
    åıįèħIJåĢ¡å»ī
    -0.10
    æŃ¹
    -0.09
    _behavior
    -0.09
    åĩĮæĻ¨
    -0.09
    antan
    -0.09
    uent
    -0.08
    å¿ĥåºķ
    -0.08
    æ±Ĭ
    -0.08
    æīĵè¿Ľ
    -0.08
    POSITIVE LOGITS
    ÑĢак
    0.09
     hurt
    0.08
    ibel
    0.08
    身
    0.08
    agg
    0.08
    åīĬåĩı
    0.08
    宣åijĬ
    0.08
    å²ij
    0.08
    åħ¶éĹ´
    0.08
     Vim
    0.08
    Activations Density 0.207%

    No Known Activations