© 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. 1351
    Prev
    Next
    INDEX
    Explanations

    waiver, override, delegated

    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
    æĴĩ
    -0.21
    ingle
    -0.20
    ä¸Ģç»Ħ
    -0.20
     transforming
    -0.20
     afar
    -0.20
    ä¸Ģåıª
    -0.20
     waves
    -0.19
     unemployed
    -0.19
    éĹ¹
    -0.19
    tern
    -0.18
    POSITIVE LOGITS
    0.26
    ew
    0.24
    ä¸įå¼Ģ
    0.24
    /disable
    0.23
    ä»»ä½ķå½¢å¼ı
    0.22
     gegenüber
    0.22
    æİī
    0.22
    ointment
    0.20
     pragma
    0.20
    ktor
    0.20
    Activations Density 0.007%

    No Known Activations