© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 2352
    Prev
    Next
    INDEX
    Explanations

    was/were + found/Reg/John/types

    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
    CAA
    -0.26
    æīĢéľĢ
    -0.23
     Detaylı
    -0.23
    Fixture
    -0.23
    aÄŁa
    -0.22
    ESA
    -0.22
    CSI
    -0.22
     ÑĤек
    -0.21
    æ±Ĥ
    -0.21
    olatile
    -0.21
    POSITIVE LOGITS
    æĺ¯ä»Ģä¹Īåij¢
    0.32
    æĿ¥èĩªäºİ
    0.32
    ä»Ģä¹Īåij¢
    0.31
    èİ«è¿ĩäºİ
    0.30
    åı¯æĥ³èĢĮçŁ¥
    0.30
    å¦Ĥä¸ĭ
    0.27
     nämlich
    0.27
    以ä¸ĭåĩłä¸ª
    0.27
    :
    0.26
    ä¾Ĩèĩª
    0.26
    Activations Density 0.224%

    No Known Activations