© 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. 240
    Prev
    Next
    INDEX
    Explanations

    all out, full effort, best abilities

    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
    ä¸į便
    -0.28
    ä¸įæĸ¹ä¾¿
    -0.25
     omin
    -0.24
    æĸ¹ä¾¿
    -0.23
    踪
    -0.23
     nuisance
    -0.22
    群
    -0.22
    æķ´æ´ģ
    -0.22
     dumpster
    -0.21
    ç¢į
    -0.21
    POSITIVE LOGITS
    åħ¨åĬĽä»¥èµ´
    0.40
    æĬķåħ¥
    0.39
    æĬķåħ¥åĪ°
    0.38
    åħ¨åĬĽ
    0.36
     effort
    0.36
    æĭ¼æIJı
    0.34
    ç«Ń
    0.34
    åħħæ²Ľ
    0.31
     fullest
    0.30
    å¥ĭæĸĹ
    0.28
    Activations Density 0.019%

    No Known Activations