© 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. 29423
    Prev
    Next
    INDEX
    Explanations

    .Writer .Html Exception

    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
    å¤±æľĽ
    -0.10
     thác
    -0.10
    .za
    -0.09
    ecided
    -0.09
    regist
    -0.09
    ä¹ĭæīĢ以
    -0.09
    åıĪ好
    -0.08
    -eyed
    -0.08
    æ¯Ķè¼ĥ
    -0.08
    stellung
    -0.08
    POSITIVE LOGITS
    s
    0.11
    sWith
    0.11
    ä¸Ģæĸ¹
    0.09
    åĨµ
    0.09
    o
    0.09
    .Writer
    0.08
    çĶ¨åĵģ
    0.08
    andel
    0.08
    sburg
    0.08
    åĪ¨
    0.08
    Activations Density 0.001%

    No Known Activations