© 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. 2430
    Prev
    Next
    INDEX
    Explanations

    kind or types

    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
    æĦıå¿Ĺ
    -0.24
     Themes
    -0.24
    themes
    -0.23
     tiêu
    -0.23
    é«ĺçļĦ
    -0.23
    Themes
    -0.23
    çݯèĬĤ
    -0.22
     fie
    -0.22
    oad
    -0.21
    ä½į
    -0.21
    POSITIVE LOGITS
    ä½Ĩä¸įéĻIJäºİ
    0.28
    åIJĦæł·
    0.26
    æ¶ī
    0.23
    çĶ·å£«
    0.22
    eker
    0.22
     involving
    0.22
    æ°ijçĶ¨
    0.21
    iko
    0.21
    对èĩªå·±çļĦ
    0.21
    unning
    0.21
    Activations Density 0.031%

    No Known Activations