© 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. 3108
    Prev
    Next
    INDEX
    Explanations

    fishing or sports equipment

    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
    Not in Any Lists

    No Comments

    Negative Logits
    å¨ĺ家
    -0.10
    轸
    -0.09
    aise
    -0.09
    åĽŀé¦Ī
    -0.09
    atum
    -0.08
    пÑĭ
    -0.08
    å®£ä¼łæķĻèĤ²
    -0.08
    issen
    -0.08
    punk
    -0.08
    æĥ«
    -0.08
    POSITIVE LOGITS
    ä¸ĵæłı
    0.10
    .getParam
    0.09
    ä½¥
    0.09
    íĭ±
    0.09
    åģļæ³ķ
    0.09
     uda
    0.09
    igaret
    0.09
    鸳
    0.09
    ç¦ģ
    0.08
    æľĿ
    0.08
    Activations Density 0.011%

    No Known Activations