© 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. 43
    Prev
    Next
    INDEX
    Explanations

    hearing protection, light-colored, lifts, fruit, low-fat, healthy choices, coupons, UTF-8, block ads, technologies

    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
     Hole
    -0.24
    èĪĴéĢĤ
    -0.24
    æĥ³è¦ģ
    -0.24
    磮
    -0.23
    WithError
    -0.23
    áb
    -0.23
    建档
    -0.23
     privacy
    -0.23
    æ§Ľ
    -0.23
    éļIJç§ģ
    -0.23
    POSITIVE LOGITS
    çŃīæĸ¹å¼ı
    0.25
    ãģıãĤĮ
    0.23
     whenever
    0.23
    çŃīåIJĦç§į
    0.22
    çŃīè¡Įä¸ļ
    0.22
    çŃīå¤ļç§į
    0.22
    çŃīå·¥ä½ľ
    0.21
    Google
    0.21
    éļıå¤Ħåı¯è§ģ
    0.21
    æ¸Ŀ
    0.21
    Activations Density 0.085%

    No Known Activations