© 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. 27766
    Prev
    Next
    INDEX
    Explanations

    copyright notice identifiers

    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
    æĴĩ
    -0.08
    åĮĸçļĦ
    -0.08
    åºĻ
    -0.08
    åĿIJ
    -0.07
    宣讲
    -0.07
    æĿ¥å®¾
    -0.07
    人大代表
    -0.07
    ëħ¼
    -0.07
     OR
    -0.07
    人æĢ§
    -0.07
    POSITIVE LOGITS
    çīĪæĿĥæīĢæľī
    0.11
    copyright
    0.11
    ä½ľèĢħæīĢæľī
    0.11
     каÑĩ
    0.10
    å¾Īå¤ļäºĭæĥħ
    0.10
    å¿ĥçĸ¼
    0.10
     tph
    0.10
     COPYRIGHT
    0.09
    çī¹åĪ«å£°æĺİ
    0.09
    èĩªè´Ł
    0.09
    Activations Density 0.230%

    No Known Activations