© 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. 7749
    Prev
    Next
    INDEX
    Explanations

    listing examples or series

    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
    èļĢ
    -0.10
    æĸ½
    -0.09
    æĪļ
    -0.09
    éĺģ
    -0.09
    åħīéĺ´
    -0.08
    dirs
    -0.08
    æĿ¥èĩª
    -0.08
    椴
    -0.08
    驸
    -0.08
    è·ŁæĪij
    -0.08
    POSITIVE LOGITS
    åĨįåĪ°
    0.19
    çĶļèĩ³
    0.12
    ä¹ĥèĩ³
    0.12
    ãģĿãģĹãģ¦
    0.11
    åıĪ被
    0.10
    çĶļèĩ³è¿ĺ
    0.10
    è¿ĽèĢĮ
    0.10
     cere
    0.09
     onto
    0.09
    æ½®
    0.09
    Activations Density 0.102%

    No Known Activations