© 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. 11417
    Prev
    Next
    INDEX
    Explanations

    stop/close/off states

    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
    æ·ĸ
    -0.21
    ioni
    -0.20
    sons
    -0.20
    æ³¼
    -0.19
     Lynch
    -0.19
    anches
    -0.19
    éĿ¢è²Į
    -0.19
    oble
    -0.18
    æīĭèħķ
    -0.18
    å¿Ŀ
    -0.18
    POSITIVE LOGITS
    åĨįåİ»
    0.26
    çĦ¶åIJİåĨį
    0.24
    åIJİåĨį
    0.23
    æİī
    0.20
    ãĤ·ãĤ¢
    0.20
    ä¹ĭåIJİ
    0.19
     followed
    0.19
    WithError
    0.18
    tight
    0.18
    ">ÃĹ</
    0.18
    Activations Density 0.074%

    No Known Activations