© 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. 984
    Prev
    Next
    INDEX
    Explanations

    making difference-maker

    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
    rust
    -0.26
    漫éķ¿çļĦ
    -0.23
    æĪĸèĢħåħ¶ä»ĸ
    -0.22
    rec
    -0.22
    Ñĩем
    -0.22
    alphabet
    -0.22
    åºŀ大çļĦ
    -0.21
     Rec
    -0.21
    rig
    -0.20
    大èĩ´
    -0.20
    POSITIVE LOGITS
     deeds
    0.29
    ä¹ĭ举
    0.28
     necessary
    0.27
    sWith
    0.25
    ä¸ĢæĬĬ
    0.25
    å¿ħè¦ģçļĦ
    0.25
     DAMAGES
    0.24
    åIJ¦åĪĻ
    0.23
     surg
    0.23
    necessary
    0.23
    Activations Density 0.009%

    No Known Activations