© 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. 2092
    Prev
    Next
    INDEX
    Explanations

    US cities and places

    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
    äºĶå¹´
    -0.24
    æļĤ
    -0.23
    å¹´ä¹ĭä¹ħ
    -0.23
    ä¸īå¹´
    -0.23
    avigation
    -0.22
    åīįä¸ĸ
    -0.22
    _CLASSES
    -0.22
    ä¸ĥå¹´
    -0.22
     reinc
    -0.21
    .Year
    -0.21
    POSITIVE LOGITS
    æľ¬æĬ¥è®¯
    0.34
    ç½ij讯
    0.28
    åºĵéĩĮ
    0.26
    ville
    0.26
    æľ¬æĬ¥è®°èĢħ
    0.25
    åĪ©
    0.24
    è®°èĢħåľ¨
    0.24
    è®°èĢħ
    0.24
    æĸ°åįİ社
    0.23
    ä»ĸ表示
    0.23
    Activations Density 0.189%

    No Known Activations