© 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. 1316
    Prev
    Next
    INDEX
    Explanations

    huge amounts

    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
    aret
    -0.25
     studio
    -0.25
    ago
    -0.24
     bilingual
    -0.23
     reform
    -0.23
    æ¯Ķè¾ĥ好
    -0.22
    æĶ¹éĿ©
    -0.22
    aben
    -0.22
    -side
    -0.22
    è°ĩ
    -0.22
    POSITIVE LOGITS
    巨大
    0.50
     immense
    0.47
     enorm
    0.46
    åºŀ大
    0.45
    巨大çļĦ
    0.45
    空åīį
    0.45
     huge
    0.44
     enormous
    0.44
    çļĦ巨大
    0.43
    åºŀ大çļĦ
    0.43
    Activations Density 0.099%

    No Known Activations