© 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. 37462
    Prev
    Next
    INDEX
    Explanations

    prehistoric creatures

    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
    åŃķ
    -0.10
    åı¤èĢģ
    -0.10
    è¿ĩåİ»çļĦ
    -0.09
    åĽŀæļĸ
    -0.09
     cup
    -0.09
    å²Ľ
    -0.09
    åĵī
    -0.09
    anson
    -0.09
    oftware
    -0.09
    itals
    -0.09
    POSITIVE LOGITS
    墨
    0.09
    ÙĨص
    0.08
    riv
    0.08
     Sher
    0.08
    ãĤ·ãĥ³
    0.08
     provid
    0.08
    çį»
    0.08
     yok
    0.08
    称ä¹ĭ为
    0.08
     caractère
    0.08
    Activations Density 0.011%

    No Known Activations