© 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. 930
    Prev
    Next
    INDEX
    Explanations

    most influential people lists

    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
    åľ¨ä¸ĢæĹģ
    -0.25
    å°ı女åŃ©
    -0.24
    æĶ¶æķĽ
    -0.23
    åł¤
    -0.23
    大éĩı
    -0.22
    =YES
    -0.22
    大éĩıçļĦ
    -0.21
    imson
    -0.21
     decor
    -0.21
    illage
    -0.21
    POSITIVE LOGITS
    åIJįå½ķ
    0.33
    æ¦ľ
    0.32
    æ¦ľåįķ
    0.30
     rankings
    0.30
    åIJįåįķ
    0.30
    æİĴè¡Įæ¦ľ
    0.28
    åĪĨåĪ«æĺ¯
    0.28
     nationally
    0.27
    æİĴåIJį
    0.27
     list
    0.26
    Activations Density 0.048%

    No Known Activations