© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 1793
    Prev
    Next
    INDEX
    Explanations

    correction of errors

    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
    rium
    -0.26
    LTR
    -0.24
    æ¯ĶæĪij
    -0.24
    åĴ±ä»¬
    -0.24
    çݰ代社ä¼ļ
    -0.24
    æĻºæħ§
    -0.23
     stuff
    -0.23
    èѬå¦Ĥ
    -0.23
     constantly
    -0.23
    æ¯Ķå¦Ĥ说
    -0.23
    POSITIVE LOGITS
     incorrectly
    0.39
     mistakenly
    0.34
    误导
    0.29
    åĪĬçĻ»
    0.29
     previously
    0.28
     incorrect
    0.28
     wrongly
    0.28
    误
    0.27
     erroneous
    0.27
     inadvert
    0.27
    Activations Density 0.030%

    No Known Activations