© 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. 2374
    Prev
    Next
    INDEX
    Explanations

    combined and cumulative totals

    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
    rag
    -0.24
    roat
    -0.24
    èĮµ
    -0.22
    çĽĴåŃIJ
    -0.22
    顺åĬ¿
    -0.21
    MethodManager
    -0.21
    æľºéģĩ
    -0.21
    اØŃ
    -0.21
    笼
    -0.21
     cảnh
    -0.20
    POSITIVE LOGITS
    åľ¨ä¸Ģèµ·
    0.33
     Together
    0.32
    åIJĪ计
    0.31
     collectively
    0.28
    Together
    0.27
     together
    0.27
    åįłæ¯Ķ
    0.26
    æĢ»åħ±
    0.24
    åįĬå°ıæŶ
    0.24
     cumulative
    0.23
    Activations Density 0.024%

    No Known Activations