© 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. 9039
    Prev
    Next
    INDEX
    Explanations

    line of sight

    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
    ä¸ĭæĿ¥çļĦ
    -0.10
     INCLUDED
    -0.09
    éķ¿èĢģ
    -0.09
    æ±¾
    -0.09
    ÙĩÙĨ
    -0.09
     Preston
    -0.09
     Caucus
    -0.08
    çĹķ
    -0.08
     honor
    -0.08
    çĽ¥
    -0.08
    POSITIVE LOGITS
    è§Ĩ线
    0.12
    çľ¼çļ®
    0.10
    çľ¼åīį
    0.10
    æĸ°äºº
    0.10
    ä¸Ģ线
    0.09
    Ãły
    0.09
    楼
    0.09
    åĩºçİ°åľ¨
    0.09
    Tip
    0.09
    主æµģ
    0.09
    Activations Density 0.041%

    No Known Activations