© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 1599
    Prev
    Next
    INDEX
    Explanations

    Mac, MacBook, Macintosh

    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
     BUFF
    -0.23
    è¯Ĩ
    -0.23
    æĦıä¹īä¸ĬçļĦ
    -0.23
     pinch
    -0.22
    飧
    -0.22
     debounce
    -0.22
    飧æĢ§
    -0.22
    èŃĺ
    -0.21
    åĬŀäºĭå¤Ħ
    -0.21
     Disorder
    -0.21
    POSITIVE LOGITS
    åı°
    0.28
    æ¡ĮéĿ¢
    0.28
     desktop
    0.26
    彩èī²
    0.26
    å¢Ļ
    0.24
    çIJīçĴĥ
    0.23
    è£ħä¿®
    0.23
    ç¬ijèĦ¸
    0.23
     glass
    0.22
    å£ģçĶ»
    0.22
    Activations Density 0.003%

    No Known Activations