© 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. 54116
    Prev
    Next
    INDEX
    Explanations

    take measures to ensure

    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
    VERR
    -0.09
    éļı便
    -0.09
    æĺ¯ä¸Ģ座
    -0.09
     eo
    -0.09
    è¿Ļä¸ªåľ°æĸ¹
    -0.09
    æį¢ä¸ª
    -0.09
    toa
    -0.08
    ооÑĢ
    -0.08
    åĨľå®¶
    -0.08
    èĽ³
    -0.08
    POSITIVE LOGITS
    æݪæĸ½
    0.28
     measures
    0.20
    举æݪ
    0.18
     Measures
    0.17
    æݪ
    0.14
    æīĭ段
    0.13
     measure
    0.13
     Measure
    0.13
     medidas
    0.12
    measure
    0.12
    Activations Density 0.054%

    No Known Activations