© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12198
    Prev
    Next
    INDEX
    Explanations

    precious metals and cryptocurrency

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    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
    Dismiss
    -0.20
    .jet
    -0.20
    æĸŁ
    -0.19
    ä¸ĩåįĥ
    -0.19
    atic
    -0.19
    -banner
    -0.18
    _EXIT
    -0.18
     büt
    -0.18
    ahir
    -0.17
    æµģ失
    -0.17
    POSITIVE LOGITS
    -backed
    0.25
    é¦ĸ饰
    0.20
     Sole
    0.20
    èĥĮ
    0.19
     backed
    0.19
     Hers
    0.18
     backing
    0.18
    为代表
    0.18
    æ¯Ķçİĩ
    0.18
    éļĨ
    0.17
    Activations Density 0.027%

    No Known Activations