© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 76
    Prev
    Next
    INDEX
    Explanations

    court decisions dates

    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
     Outlet
    -0.26
     polo
    -0.24
    ä¸Ģæīĭ
    -0.24
     outlet
    -0.24
    æĹ©çĤ¹
    -0.24
    :return
    -0.23
    éºĿ
    -0.23
    æĹ©æľŁ
    -0.23
    æľªæĿ¥åıijå±ķ
    -0.23
    Outlet
    -0.22
    POSITIVE LOGITS
    âĨµ
    0.27
    nia
    0.25
     McG
    0.23
     Robert
    0.22
    .sidebar
    0.21
     Republic
    0.21
    mb
    0.21
     Cust
    0.21
     attorneys
    0.21
    Ñī
    0.20
    Activations Density 0.278%

    No Known Activations