© 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. 691
    Prev
    Next
    INDEX
    Explanations

    etiology or cause

    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
     ideals
    -0.26
     ideal
    -0.23
    çIJĨæĥ³çļĦ
    -0.23
    çļĦçIJĨæĥ³
    -0.23
    .CreateCommand
    -0.22
    ewise
    -0.21
    edelta
    -0.21
    å¿ĥçIJĨ
    -0.21
    -style
    -0.21
    æĬĬèĩªå·±çļĦ
    -0.21
    POSITIVE LOGITS
    ä¸įæĺİ
    0.39
    æľªçŁ¥
    0.31
    unknown
    0.29
     undisclosed
    0.29
    ilio
    0.28
    ä¸įæ¸ħæ¥ļ
    0.28
    ä¸įæ¸ħ
    0.28
     unspecified
    0.27
     unknown
    0.26
    çĸijä¼¼
    0.26
    Activations Density 0.093%

    No Known Activations