© 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. 1330
    Prev
    Next
    INDEX
    Explanations

    posting classifieds and submissions

    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
     excursion
    -0.23
     Combined
    -0.22
     overall
    -0.22
    Combined
    -0.22
     liqu
    -0.21
    éªļ
    -0.21
    prox
    -0.21
    åĩºåĬ¨
    -0.21
     plane
    -0.21
     closest
    -0.21
    POSITIVE LOGITS
     submissions
    0.33
    ä¸Ĭä¼ł
    0.29
    ä¸įæĸŃå¢ŀåĬł
    0.28
    å½ķåħ¥
    0.27
    æŶæķĪ
    0.27
    æ·»åĬł
    0.27
    åħ¥åı£
    0.26
    uzzi
    0.26
    æıIJ交
    0.25
    è¿ĽæĿ¥
    0.25
    Activations Density 0.235%

    No Known Activations