© 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. 53479
    Prev
    Next
    INDEX
    Explanations

    HTML/XML structure tags

    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
    麻辣
    -0.10
    pus
    -0.08
     sanity
    -0.08
    è¨ĩ
    -0.08
    å·²ä¹ħçļĦ
    -0.08
    æŶéĹ´ä¸º
    -0.08
     McDon
    -0.08
    èĮĢ
    -0.08
     пÑĢид
    -0.08
     Specialty
    -0.08
    POSITIVE LOGITS
     rather
    0.08
    æĴĤ
    0.08
    Ê·
    0.08
    ãģĤãĤĮ
    0.07
     exactly
    0.07
    ãģĿãģĵãģ«
    0.07
    æķ·
    0.07
    绵
    0.07
    åijµ
    0.07
    沦
    0.07
    Activations Density 1.482%

    No Known Activations