© 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. 60983
    Prev
    Next
    INDEX
    Explanations

    has/have been

    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
    å·²ç»ı
    -0.11
    ä¸ĢäºĽ
    -0.10
    æĹ©å·²
    -0.09
    æľīæķĪæľŁ
    -0.09
    è¿Ļæīį
    -0.09
    å·²ç»ıåľ¨
    -0.09
    çİ°åľ¨çļĦ
    -0.09
    ä¸Ģ種
    -0.09
    ä¸Ģ个å°ı
    -0.08
    å½ĵå¹´
    -0.08
    POSITIVE LOGITS
    adoo
    0.09
    _attempt
    0.09
    acre
    0.09
    /w
    0.08
    extras
    0.08
    åĤ¨èĥ½
    0.08
    ór
    0.08
    emode
    0.08
    ãģĦãģĭ
    0.08
    /current
    0.08
    Activations Density 0.242%

    No Known Activations