© 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. 32467
    Prev
    Next
    INDEX
    Explanations

    study findings

    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
    cape
    -0.10
    çļĦéĤ£ä¸Ģ
    -0.10
    åĨĮ
    -0.09
    éĤ£æŶ
    -0.09
    èī°è¾Ľ
    -0.08
    åĿİåĿ·
    -0.08
    åıĻ
    -0.08
    èħ´
    -0.08
    æĹ¥å¸¸å·¥ä½ľ
    -0.08
    å°ģ
    -0.08
    POSITIVE LOGITS
    oser
    0.09
    ahl
    0.08
     اÙĦتاب
    0.08
     Dep
    0.08
    ä½łçİ°åľ¨
    0.08
    åĩºçİ°åľ¨
    0.08
    æĪĸå¤ļ
    0.08
    enge
    0.08
    æī¾åĪ°äºĨ
    0.08
    æ²±
    0.08
    Activations Density 0.131%

    No Known Activations