© 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. 17393
    Prev
    Next
    INDEX
    Explanations

    continuous production/flow/measure/function

    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®ļäºĨ
    -0.10
    ä¸ĢæŶ
    -0.10
    ä¸Ģåħ±
    -0.09
    ä¸ĢåĪĩéĥ½æĺ¯
    -0.09
    ä¸ĢåĪĩ
    -0.09
    çĨ¹
    -0.09
    .getNode
    -0.08
    ÅIJ
    -0.08
    æľ¬èĥ½
    -0.08
    åħ¨éĿ¢èIJ½å®ŀ
    -0.08
    POSITIVE LOGITS
    ä¸įéĹ´æĸŃ
    0.13
    ä¸įæĸŃçļĦ
    0.12
    ä¸įæĸŃåľ°
    0.11
    æĢ§çļĦ
    0.11
    lest
    0.11
     Improvement
    0.10
    IBLE
    0.10
    monitor
    0.10
    çħ½
    0.10
     uninterrupted
    0.09
    Activations Density 0.042%

    No Known Activations