© 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. 59468
    Prev
    Next
    INDEX
    Explanations

    neighborhoods and political issues

    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
    æĴħ
    -0.10
    å¤§éĽ¨
    -0.10
    æĮ¯åħ´
    -0.09
    ÙĬÙĪÙĨ
    -0.09
    ysz
    -0.09
    ä¸ĩäºĭ
    -0.09
    åįĩ温
    -0.08
    lobber
    -0.08
    æ°Ł
    -0.08
    ãĥ§
    -0.08
    POSITIVE LOGITS
    dit
    0.09
    çĤĻ
    0.08
    ä¹ĭåĬ¿
    0.08
    _seen
    0.08
    ãģĹãģª
    0.08
    çħ²
    0.08
    åģĥ
    0.08
    _glob
    0.08
    fw
    0.07
     Paz
    0.07
    Activations Density 0.340%

    No Known Activations