© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 35752
    Prev
    Next
    INDEX
    Explanations

    records of data

    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
     ÑĢож
    -0.10
    .bootstrap
    -0.10
    åij¼åĴĮ
    -0.10
    ä¸ĢåIJį
    -0.09
    ë¶Ī
    -0.09
    صØŃ
    -0.09
    éģ¥
    -0.09
    ALE
    -0.08
    åĹ¡
    -0.08
     Unsure
    -0.08
    POSITIVE LOGITS
    æľ¬ç½ijç«Ļ
    0.12
    beck
    0.12
    è¶³å¤Ł
    0.09
    çŃ®
    0.09
    å®Įæķ´
    0.09
    went
    0.09
     data
    0.09
    æķ°æį®
    0.09
    é½IJåħ¨
    0.09
    æľīæĦıä¹ī
    0.09
    Activations Density 0.147%

    No Known Activations