© 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. 934
    Prev
    Next
    INDEX
    Explanations

    life insurance, assurance, Universal

    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
    éĨĭ
    -0.29
    æĶĺ
    -0.27
    scape
    -0.25
     Washing
    -0.25
    patch
    -0.24
    åľī
    -0.24
     washed
    -0.24
     separat
    -0.24
     Paste
    -0.24
    Reuse
    -0.24
    POSITIVE LOGITS
    人寿
    0.39
    ä¿ĿéĻ©
    0.34
    Premium
    0.34
    ä¿ĿéĻ©åħ¬åı¸
    0.33
    ä¿Ŀè´¹
    0.33
    åıĹçĽĬ
    0.32
     premiums
    0.32
    åħ¬ç§¯éĩij
    0.30
    premium
    0.30
    çIJĨ财产åĵģ
    0.29
    Activations Density 0.012%

    No Known Activations