© 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. 288
    Prev
    Next
    INDEX
    Explanations

    words ending in ically or ually

    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
    ever
    -0.25
    å¾Ģå¾Ģä¼ļ
    -0.25
    perhaps
    -0.25
     perhaps
    -0.23
    ful
    -0.23
    æĢ§çĸ¾çĹħ
    -0.23
    ðŁ¤Ķ
    -0.22
    å®ŀåľ¨æĺ¯å¤ª
    -0.21
     mainly
    -0.21
    ãģ¹ãģį
    -0.21
    POSITIVE LOGITS
     outright
    0.27
     nonexistent
    0.26
    åįĬ个
    0.25
    ually
    0.23
    .TryParse
    0.23
     decay
    0.22
     bá»ı
    0.22
    ä¸įåı¯èĥ½
    0.21
     annihil
    0.21
    à¹Ģลย
    0.21
    Activations Density 0.008%

    No Known Activations