© 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. 1301
    Prev
    Next
    INDEX
    Explanations

    public transparency and accountability

    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
    åı¹æģ¯
    -0.25
    sad
    -0.24
    夹
    -0.24
    æĭ³
    -0.23
     sad
    -0.23
     Toni
    -0.23
    ели
    -0.23
    åĸĩåıŃ
    -0.22
    èĥĨ
    -0.22
    çļĦ人çī©
    -0.22
    POSITIVE LOGITS
     Transparency
    0.42
     transparency
    0.39
    åħ¬ä¼Ĺ
    0.38
    éĢıæĺİ
    0.37
    çĽijçĿ£
    0.35
    åIJĮæĦı
    0.35
     democratic
    0.33
     transparent
    0.32
    审议
    0.32
     watchdog
    0.32
    Activations Density 0.160%

    No Known Activations