© 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. 782
    Prev
    Next
    INDEX
    Explanations

    funeral and burial services

    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
    笥
    -0.25
    bat
    -0.24
     Tire
    -0.23
     getattr
    -0.23
    åħ³éĶ®æĺ¯
    -0.23
    ноÑģÑĤ
    -0.22
    èµĭäºĪ
    -0.22
    /operator
    -0.22
    agged
    -0.22
     tire
    -0.21
    POSITIVE LOGITS
     funeral
    0.46
    èij¬
    0.43
    殡
    0.41
     mourning
    0.40
    棺
    0.39
     Funeral
    0.37
     burial
    0.37
     mourn
    0.35
     coffin
    0.35
    丧
    0.35
    Activations Density 0.021%

    No Known Activations