© 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. 60839
    Prev
    Next
    INDEX
    Explanations

    DNA extraction and isolation

    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
    ISTER
    -0.09
    è¾IJå°Ħ
    -0.09
    è¯ķæİ¢
    -0.09
    æ°Ł
    -0.09
    åĽºå®ļçļĦ
    -0.09
    olle
    -0.09
    oron
    -0.08
    ä¸įæĿ¥
    -0.08
     nâ
    -0.08
    åıĺæĢģ
    -0.08
    POSITIVE LOGITS
    æ£Ģ
    0.09
    æıIJåıĸ
    0.09
    Lane
    0.08
    Cargo
    0.08
     extracts
    0.08
     peak
    0.08
    ç»°
    0.08
    åĨ¼
    0.08
    оÑī
    0.08
     extract
    0.08
    Activations Density 0.129%

    No Known Activations