© 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. 8721
    Prev
    Next
    INDEX
    Explanations

    events and parties

    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
    åıĤåĬłäºĨ
    -0.10
    nees
    -0.09
    داد
    -0.09
    Checked
    -0.09
    åĪĩ
    -0.09
     ÑħаÑĢакÑĤеÑĢиÑģÑĤ
    -0.09
    åı®
    -0.08
    åľ¨çº¿åĴ¨è¯¢
    -0.08
     junior
    -0.08
    /operator
    -0.08
    POSITIVE LOGITS
     verr
    0.10
    æĭİ
    0.09
    缮çļĦ
    0.09
    表彰
    0.09
    åĶ¤éĨĴ
    0.08
    .openapi
    0.08
    agle
    0.08
    è²Ĥ
    0.08
    ä¸ºçĽ®çļĦ
    0.08
    åİĭæĬij
    0.08
    Activations Density 0.026%

    No Known Activations