© 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. 749
    Prev
    Next
    INDEX
    Explanations

    Fox, Sports, News, Woods, Lane

    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
    翻身
    -0.10
    å¿ĥå¢ĥ
    -0.09
    èĽĻ
    -0.09
    èºģ
    -0.09
    åıijçĹħ
    -0.08
    éł
    -0.08
     Greenwood
    -0.08
    åıĤèĤ¡
    -0.08
    åĽ½åº¦
    -0.08
    马æĭī
    -0.08
    POSITIVE LOGITS
    箩
    0.09
    çĭIJ
    0.09
    _dirty
    0.09
    ìłł
    0.08
    ORT
    0.08
    åĬĽæ±Ĥ
    0.08
     pry
    0.08
    äºĨäºĽ
    0.08
    iaux
    0.08
    æįħ
    0.08
    Activations Density 0.023%

    No Known Activations