© 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. 20404
    Prev
    Next
    INDEX
    Explanations

    visual density

    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
    åŁĭ
    -0.08
    åĥı个
    -0.08
     Stamp
    -0.08
    ago
    -0.08
    chron
    -0.08
     Performing
    -0.08
    å°Ĭ
    -0.08
    å¼Ģ头
    -0.08
    ival
    -0.08
     elev
    -0.08
    POSITIVE LOGITS
    çļĦé¢ľèī²
    0.11
    é¢ľèī²
    0.10
     Pant
    0.10
    åŀ©
    0.10
    é¡ı
    0.10
    å®ŀçī©
    0.10
    çģ¯åħī
    0.10
    è¿ĺåİŁ
    0.09
    åģıåIJij
    0.09
    å®ŀä½ĵåºĹ
    0.09
    Activations Density 0.071%

    No Known Activations