© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 14582
    Prev
    Next
    INDEX
    Explanations

    goblins or goblins_and

    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
    LAG
    -0.21
    æķ¢
    -0.20
    çĻ½é©¬
    -0.20
    .band
    -0.20
    é£İæĻ¯
    -0.20
    纵横
    -0.19
    è¿ľæĸ¹
    -0.18
    FML
    -0.18
    åľ¨åħ¨çIJĥ
    -0.18
    æ¨ĺ
    -0.18
    POSITIVE LOGITS
    ibaba
    0.20
    aisal
    0.20
    throat
    0.19
    磻
    0.19
    è°Ģ
    0.18
     breathed
    0.18
     ÐijолÑĮÑĪ
    0.17
    /uploads
    0.17
    骨头
    0.17
    骸
    0.17
    Activations Density 0.001%

    No Known Activations