© 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. 15476
    Prev
    Next
    INDEX
    Explanations

    career, location, history, designation

    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
    -Sah
    -0.20
    éķ¿å¤§äºĨ
    -0.20
    è¦ģåģļåĪ°
    -0.19
    iges
    -0.19
    onom
    -0.18
    æĦŁè§īèĩªå·±
    -0.18
    ardo
    -0.18
    ey
    -0.18
    éĹ®é¢ĺæĺ¯
    -0.18
    çĬ¹å¦Ĥ
    -0.18
    POSITIVE LOGITS
    _blocked
    0.20
     ê¶Į
    0.19
    subjects
    0.19
    å½»
    0.19
     má
    0.19
    çĭ¸
    0.19
    <tbody
    0.18
    ï¿
    0.18
    主ä¸ļ
    0.18
    shint
    0.17
    Activations Density 0.147%

    No Known Activations