© 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. 1108
    Prev
    Next
    INDEX
    Explanations

    against or advocating against

    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
    endif
    -0.27
    éĴ¿
    -0.24
     %%
    -0.23
    æݾ
    -0.23
     brag
    -0.23
    ISCO
    -0.23
    ä¸įèµ·
    -0.22
    交éĻħ
    -0.22
    å°ijä¸įäºĨ
    -0.22
    ä¸įæĪIJ
    -0.22
    POSITIVE LOGITS
    åIJĪçIJĨæĢ§
    0.28
     advocating
    0.28
    è´¨çĸij
    0.27
    against
    0.27
    æıIJåĩº
    0.26
     Against
    0.26
    åij¼åIJģ
    0.26
     against
    0.25
    åıį对
    0.25
    æĬ¨
    0.25
    Activations Density 0.127%

    No Known Activations