© 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. 21062
    Prev
    Next
    INDEX
    Explanations

    grade or street

    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
    款å¼ı
    -0.10
    çłľ
    -0.09
    çĪµå£«
    -0.09
     Slater
    -0.09
     aspir
    -0.09
    ItemSelected
    -0.08
    å¾ģ
    -0.08
    جاب
    -0.08
    ãĤº
    -0.08
    anse
    -0.08
    POSITIVE LOGITS
     culo
    0.09
    å·²ç»ıæľī
    0.09
    åħīèį£
    0.09
    atica
    0.09
    è¡Ķ
    0.09
    æįį
    0.09
    orage
    0.09
    åħļä¸Ń央
    0.08
    åĪģ
    0.08
    åıĹåĪ°å½±åĵį
    0.08
    Activations Density 0.088%

    No Known Activations