© 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. 641
    Prev
    Next
    INDEX
    Explanations

    insurance, premiums, company

    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
     flesh
    -0.26
    æµĵ缩
    -0.26
     multid
    -0.25
    .twitter
    -0.25
     macro
    -0.24
    Ĺı
    -0.23
    èĪŀåı°ä¸Ĭ
    -0.23
    ä¼Łå¤§
    -0.23
    éĩįå¤§é¡¹çĽ®
    -0.23
    oley
    -0.23
    POSITIVE LOGITS
     insurance
    0.40
    ä¿Ŀè´¹
    0.38
    ä¿ĿéĻ©
    0.37
     ÑģÑĤÑĢаÑħ
    0.36
    Insurance
    0.36
    çIJĨèµĶ
    0.36
     Insurance
    0.35
    çīĮçħ§
    0.35
     premiums
    0.35
    ä¿ĿéĻ©åħ¬åı¸
    0.34
    Activations Density 0.033%

    No Known Activations