© 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. 1317
    Prev
    Next
    INDEX
    Explanations

    explaining or demonstrating results

    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
     stuff
    -0.32
     wouldn
    -0.30
     wasn
    -0.29
    è¦ģçŁ¥éģĵ
    -0.28
     pretty
    -0.28
     really
    -0.27
    استÙĤÙĦ
    -0.27
     anything
    -0.27
     someone
    -0.26
     your
    -0.26
    POSITIVE LOGITS
    æݢ讨
    0.43
    éĺIJè¿°
    0.43
     elucid
    0.39
    论è¯ģ
    0.38
    éĺIJæĺİ
    0.37
    论述
    0.35
    éĺIJéĩĬ
    0.35
    çĿĢéĩį
    0.34
    æıŃ示
    0.34
     illustr
    0.33
    Activations Density 1.348%

    No Known Activations