© 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. 248
    Prev
    Next
    INDEX
    Explanations

    endometriosis or match any

    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
    è¿ijæľŁ
    -0.22
    ä¿Ŀæ´ģ
    -0.21
    oup
    -0.21
    endforeach
    -0.21
    UCH
    -0.21
     cro
    -0.20
    specs
    -0.20
    miss
    -0.20
    æĬĺæī£
    -0.20
    urrencies
    -0.20
    POSITIVE LOGITS
    æĥ³è±¡
    0.23
    稳
    0.22
    强大çļĦ
    0.22
    plete
    0.22
    å«Ĥ
    0.22
    辫
    0.22
    ç²ī
    0.22
    åIJĪåĬĽ
    0.22
    [counter
    0.21
    æĺŁçIJĥ
    0.21
    Activations Density 0.005%

    No Known Activations