© 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. 23081
    Prev
    Next
    INDEX
    Explanations

    not typical or conventional

    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
    缸è¾ĥäºİ
    -0.10
    缮
    -0.10
    UCH
    -0.09
    åĸĢ
    -0.09
    æľīæŶåĢĻ
    -0.09
    æľīæŶ
    -0.09
    ç¿ĥ
    -0.09
    åĩºæ±Ĺ
    -0.09
    å¿ĥ仪
    -0.08
    ç»Ģ
    -0.08
    POSITIVE LOGITS
    ä¼łç»ŁçļĦ
    0.14
     conventional
    0.12
    常è§Ħ
    0.12
    ä¸ĢèĪ¬çļĦ
    0.11
    ä¼łç»Ł
    0.10
    åįķ纯çļĦ
    0.10
    æĻ®éĢļçļĦ
    0.10
     traditional
    0.10
    çļĦä¼łç»Ł
    0.09
    ç®ĢåįķçļĦ
    0.09
    Activations Density 0.200%

    No Known Activations