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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20927
    Prev
    Next
    INDEX
    Explanations

    tagged with

    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
    æ±Łä¸ľ
    -0.10
     поддеÑĢжива
    -0.09
    inder
    -0.09
    績
    -0.09
    è§ģéĿ¢
    -0.09
    åķ¡
    -0.08
    ä¸ĭæĿ¥çļĦ
    -0.08
    ICA
    -0.08
    稳妥
    -0.08
    BitFields
    -0.08
    POSITIVE LOGITS
    isl
    0.10
    anst
    0.10
    elib
    0.09
     gái
    0.09
    襦
    0.09
    StdString
    0.09
    çĪ¨
    0.09
     fro
    0.08
    zimmer
    0.08
    çĻ¾å¹´
    0.08
    Activations Density 0.003%

    No Known Activations