© 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. 2712
    Prev
    Next
    INDEX
    Explanations

    refunds, compensation, credit, replacement

    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
    _LICENSE
    -0.28
    åıijæĮ¥ä½ľçĶ¨
    -0.26
    åħ¼èģĮ
    -0.24
    çĮ¬
    -0.23
    ä¸ĵèģĮ
    -0.23
    åħħåĪĨåıijæĮ¥
    -0.23
    åıijçİ°èĩªå·±
    -0.23
    èĩªèº«çļĦ
    -0.23
    capabilities
    -0.23
    Chinese
    -0.23
    POSITIVE LOGITS
    è¡¥åģ¿
    0.45
    è¡¥
    0.43
     compensation
    0.42
     refund
    0.39
     compens
    0.39
     cancellation
    0.35
     compensate
    0.35
    éĩįæĸ°
    0.34
    é¢Ŀå¤ĸ
    0.32
     extra
    0.31
    Activations Density 0.016%

    No Known Activations