© 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. 33995
    Prev
    Next
    INDEX
    Explanations

    plasma and ions

    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
    osi
    -0.09
    æĹ¥è®°
    -0.09
    etas
    -0.09
    åĮ¡
    -0.09
    åģķ
    -0.09
    ëħ¹
    -0.09
    ä¸įæĿ¥
    -0.09
    çªĿ
    -0.09
    éŃĩ
    -0.09
    dio
    -0.08
    POSITIVE LOGITS
     plasma
    0.11
     Plasma
    0.11
    书记
    0.10
    dale
    0.09
     ion
    0.09
    åĮ¯
    0.08
    éĽį
    0.08
    åĸĻ
    0.08
    æĤĦæĤĦ
    0.08
    ç¼Ģ
    0.08
    Activations Density 0.171%

    No Known Activations