© 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. 62347
    Prev
    Next
    INDEX
    Explanations

    eponymous, titular, titled tracks

    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
    ohn
    -0.09
    åīĭ
    -0.09
    atab
    -0.09
    ç»ıèIJ¥æ´»åĬ¨
    -0.08
    âľį
    -0.08
    å®´ä¼ļ
    -0.08
    æĺ¯å¦Ĥä½ķ
    -0.08
     tort
    -0.08
    _cs
    -0.08
    istributor
    -0.08
    POSITIVE LOGITS
    èĩªå®¶
    0.09
    年代
    0.09
    ossal
    0.09
    æ¡Ī
    0.08
    æİĮ
    0.08
    æĦļ
    0.08
    ades
    0.08
    å®ķ
    0.08
     NSLayoutConstraint
    0.08
    logan
    0.08
    Activations Density 0.004%

    No Known Activations