© 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. 12355
    Prev
    Next
    INDEX
    Explanations

    a followed by a noun

    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
    äºĭåĦ¿
    -0.18
    HttpContext
    -0.17
    pend
    -0.17
    çĹ¢
    -0.17
     certain
    -0.17
     pict
    -0.17
    åѦçĶŁçļĦ
    -0.17
    çĹĶ
    -0.16
    Ñħодим
    -0.16
     being
    -0.16
    POSITIVE LOGITS
    é¢ĩåħ·
    0.23
    èıĬèĬ±
    0.19
    åĪĨ彩
    0.19
    åıĮéĩį
    0.19
    ãģĬäºĴ
    0.19
    osi
    0.18
    åħ³äºİ
    0.18
    æĪĸå¤ļ
    0.18
    /is
    0.18
    ä¸įéĹ´æĸŃ
    0.18
    Activations Density 0.382%

    No Known Activations