© 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. 56260
    Prev
    Next
    INDEX
    Explanations

    numbers followed by units (°F/°C), commas, or meters

    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
    mm
    -0.08
    ine
    -0.08
    è§ĦåĪĴ设计
    -0.08
     none
    -0.08
     mama
    -0.07
    åĴĮå¹³
    -0.07
    alon
    -0.07
    ves
    -0.07
    aby
    -0.07
    åIJ¦
    -0.07
    POSITIVE LOGITS
    tridge
    0.10
    ä¹ĭæĦı
    0.10
    anford
    0.10
    æĽ´å¤ļ
    0.10
    brit
    0.10
    æłĹ
    0.10
    çļĦæĦıä¹ī
    0.09
    ÙĬب
    0.09
    éĢ¾
    0.09
    rees
    0.09
    Activations Density 0.067%

    No Known Activations