© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 997
    Prev
    Next
    INDEX
    Explanations

    punctuation followed by a word

    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
    åĮ¿
    -0.24
     sav
    -0.24
    alse
    -0.22
    ocol
    -0.22
    à¹ģà¸ĸม
    -0.22
    ë¿IJ
    -0.22
    -na
    -0.22
    GLOBALS
    -0.21
    -bre
    -0.21
     choice
    -0.21
    POSITIVE LOGITS
    çĶ±äºİ
    0.32
    çĶ±æĸ¼
    0.29
    èĩªä»İ
    0.26
    为äºĨ让
    0.24
    éļıçĿĢ
    0.24
     Firstly
    0.24
     Due
    0.24
    为äºĨ
    0.23
    æĪIJåĬŁçļĦ
    0.23
    éĿ¢ä¸´çĿĢ
    0.23
    Activations Density 0.038%

    No Known Activations