© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 365
    Prev
    Next
    INDEX
    Explanations

    multiple, various, some, others

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    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
    èĢ½è¯¯
    -0.27
     serialVersionUID
    -0.27
     Compatibility
    -0.27
     overrides
    -0.25
    åıĮèĦļ
    -0.23
    诰
    -0.23
    æĺ¯ä»ĸ
    -0.23
     overriding
    -0.22
     instructions
    -0.22
    @js
    -0.22
    POSITIVE LOGITS
    纷纷
    0.47
    åĩłå®¶
    0.45
    æ¶Įçİ°
    0.42
    æ¶Įçİ°åĩº
    0.41
    å±Ĥåĩºä¸įç©·
    0.39
    è¶ĬæĿ¥è¶Ĭå¤ļ
    0.39
    大大å°ıå°ı
    0.37
    ä¸Ģ大æī¹
    0.37
    åIJĦ家
    0.36
     dozens
    0.35
    Activations Density 0.203%

    No Known Activations