© 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. 1889
    Prev
    Next
    INDEX
    Explanations

    design ui

    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
    åĤ¨éĩı
    -0.11
    åľ¨çº¿
    -0.08
    éĶĴ
    -0.08
    åĦ²
    -0.08
    ugin
    -0.08
    åŁºåľ°
    -0.08
    éĢłåģĩ
    -0.08
    èµĦè´¨
    -0.08
    ä¹īåĬ¡
    -0.08
    è¿Ń
    -0.08
    POSITIVE LOGITS
    çĶ¨æĪ·ä½ĵéªĮ
    0.13
    çķĮéĿ¢
    0.13
     UI
    0.12
    ç¾İè§Ĥ
    0.11
    UI
    0.10
    设计
    0.10
    çļĦ设计
    0.10
     design
    0.10
     ui
    0.09
    ä½ĵéªĮ
    0.09
    Activations Density 0.145%

    No Known Activations