© 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. 289
    Prev
    Next
    INDEX
    Explanations

    against

    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
     Reserved
    -0.23
    åłĨ积
    -0.23
    太å¤ļ
    -0.22
    太大
    -0.22
     reserved
    -0.22
    严éĩįçļĦ
    -0.22
    tti
    -0.22
    åıªåī©ä¸ĭ
    -0.22
     mouths
    -0.22
    éļ¾å¿ĺ
    -0.22
    POSITIVE LOGITS
     Against
    0.28
    æıIJåĩºçļĦ
    0.26
     efforts
    0.26
    æĹ©æĹ¥
    0.26
    Against
    0.25
    çļĦåģļæ³ķ
    0.25
    AINED
    0.25
     idea
    0.24
    еÑģÑĤи
    0.24
    èĢĮä¸į
    0.24
    Activations Density 0.113%

    No Known Activations