© 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. 53798
    Prev
    Next
    INDEX
    Explanations

    news agency reports

    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
    ardo
    -0.09
    rette
    -0.09
    éĹ°
    -0.09
    人åĿĩ
    -0.09
    æŶ任
    -0.08
    ufe
    -0.08
    常åĬ¡åī¯
    -0.08
    ä¸ĸçķĮç»ıæµİ
    -0.08
    æŃ£åĽłä¸º
    -0.08
    ligt
    -0.08
    POSITIVE LOGITS
    yme
    0.10
    nown
    0.09
    åľ¨ç½ij绾ä¸Ĭ
    0.09
     Mong
    0.09
    izards
    0.09
    yon
    0.09
    .masks
    0.09
    kad
    0.09
    é¼
    0.08
     Morr
    0.08
    Activations Density 0.042%

    No Known Activations