© 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
    2. Qwen3-8B
    3. 18-RESID-BATCHTOPK-65K__L0-80
    4. 2607
    Prev
    Next
    INDEX
    Explanations

    travel and commute-related words

    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
     Affero
    -0.29
    å¹³åĩ¡
    -0.25
    软
    -0.24
    éŃĶæ³ķ
    -0.23
    åıĶ
    -0.23
    æĪ¿éĹ´éĩĮ
    -0.23
    enh
    -0.23
    ç¼Ŀ
    -0.23
    é¢Ĺ
    -0.23
    ä¹Łæĺ¯ä¸Ģç§į
    -0.23
    POSITIVE LOGITS
    沿éĢĶ
    0.32
    è¶Ĭè¿ĩ
    0.31
     accessing
    0.30
     exiting
    0.29
    西侧
    0.28
    å¾Ģè¿Ķ
    0.28
    åĤįæĻļ
    0.28
    è¿Ľåĩº
    0.27
    ç©¿è¿ĩ
    0.27
    è¿ĻæĿ¡
    0.27
    Activations Density 0.050%

    No Known Activations