© 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. 49547
    Prev
    Next
    INDEX
    Explanations

    names of people and places

    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
    enci
    -0.10
    å¯Ĩ
    -0.09
    enti
    -0.09
    许
    -0.09
    åĤįæĻļ
    -0.09
    æĻļä¸Ĭ
    -0.08
     Pens
    -0.08
     оÑĩеÑĢ
    -0.08
    nü
    -0.08
     supposedly
    -0.08
    POSITIVE LOGITS
     vard
    0.10
    å·´æĸ¯
    0.10
    kowski
    0.08
    \Modules
    0.08
    级以ä¸Ĭ
    0.08
    çľģæķĻèĤ²
    0.08
    éĢĨ转
    0.08
    ä¹Łç®Ĺ
    0.08
    åľ¨ä¹İ
    0.08
    ICC
    0.08
    Activations Density 0.271%

    No Known Activations