© 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. 13954
    Prev
    Next
    INDEX
    Explanations

    articles preceding nouns

    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
    ovic
    -0.20
    æ¯Ľ
    -0.20
    visions
    -0.20
    GINE
    -0.19
    rotch
    -0.19
    çŁŃ
    -0.18
    åħ¶ä½Ļ
    -0.17
     modne
    -0.17
    åģļåĩº
    -0.17
     '&#
    -0.17
    POSITIVE LOGITS
    ä¸ĸçķĮä¸ĬæľĢ
    0.22
    ä½łæĥ³
    0.19
    ãĤ¹ãĤ¿ãĥ¼
    0.19
    ä½łè¦ģ
    0.18
    ä½łä¹Ł
    0.18
    æĪijåĸľæ¬¢
    0.18
    ibo
    0.18
     Miranda
    0.17
    åį´åıĪ
    0.17
    åĵªæĢķ
    0.17
    Activations Density 0.637%

    No Known Activations