© 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. 6024
    Prev
    Next
    INDEX
    Explanations

    TD, touchdowns, interceptions

    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
    ä½İ头
    -0.10
    lander
    -0.09
    _ie
    -0.09
    åĶ§
    -0.09
    ä¸Ģ段
    -0.09
    éłĤ
    -0.08
    Download
    -0.08
     cr
    -0.08
    æīĵæī®
    -0.08
     Yun
    -0.08
    POSITIVE LOGITS
    å°ī
    0.10
    å£ij
    0.09
    èµĭèĥ½
    0.08
    ogh
    0.08
     Kirk
    0.08
     Moss
    0.08
    illos
    0.08
     Hopkins
    0.08
    illo
    0.08
    .Stack
    0.08
    Activations Density 0.005%

    No Known Activations