© 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. 169
    Prev
    Next
    INDEX
    Explanations

    recipe instructions

    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
    Isl
    -0.24
    çļĦéĤ£ç§į
    -0.22
    ä»ĸä»¬åľ¨
    -0.22
    éĿ¡
    -0.21
    ä¾Ĩèĩª
    -0.21
    è¿Ļä¸Ģ次
    -0.21
    oklyn
    -0.21
    å¥¹åľ¨
    -0.20
    ç¾İ好çļĦ
    -0.20
    è¿Ļ个æĹ¶ä»£
    -0.20
    POSITIVE LOGITS
    è¯Ŀ
    0.27
    çľ¼çľĭ
    0.24
    å¾Īç®Ģåįķ
    0.24
    èĥ«
    0.24
    éĶħ
    0.23
    缶
    0.23
    uffed
    0.23
     mixer
    0.23
    stantiate
    0.22
    hardt
    0.22
    Activations Density 0.006%

    No Known Activations