© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9064
    Prev
    Next
    INDEX
    Explanations

    commercial applications and licenses

    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
    akra
    -0.10
    åĽ´
    -0.09
    irate
    -0.09
    æ¼ı
    -0.09
    erne
    -0.09
    åħ¨åĽ½äººæ°ij
    -0.09
    æĥ¡
    -0.09
    æ¯ķç«Ł
    -0.09
    çłĶ究åijĺ
    -0.09
    åģ¥
    -0.09
    POSITIVE LOGITS
     Clarkson
    0.10
    èµĢ
    0.09
    è°
    0.09
    æ´»åĬ¨
    0.09
    WithContext
    0.09
    æĸ°è½¦
    0.08
    itches
    0.08
    ga
    0.08
    åĵĨ
    0.08
    å§ĭäºİ
    0.07
    Activations Density 0.022%

    No Known Activations