© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 11803
    Prev
    Next
    INDEX
    Explanations

    Mozilla Public License

    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
    个å¤ļ
    -0.10
    nod
    -0.09
    SELL
    -0.09
    ä¸ªåĽ½å®¶
    -0.09
    å»ī
    -0.09
    ä»ĸæĺ¯ä¸Ģ个
    -0.09
    éģ½
    -0.09
    æľ¬ç½ij
    -0.09
    æĸ°å½¢åĬ¿
    -0.09
    Ñģоб
    -0.09
    POSITIVE LOGITS
    涯
    0.08
     bisexual
    0.08
    edImage
    0.08
     Arms
    0.08
    zug
    0.08
    大éģĵ
    0.08
    .appspot
    0.08
    uggage
    0.08
    UCT
    0.08
    ectomy
    0.08
    Activations Density 0.019%

    No Known Activations