© 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. 11414
    Prev
    Next
    INDEX
    Explanations

    time with time zones

    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
    为ä¹ĭ
    -0.21
    indy
    -0.21
     rem
    -0.19
    UED
    -0.18
     recip
    -0.18
     res
    -0.18
     reb
    -0.17
    éĶĿ
    -0.17
     inde
    -0.17
    ÐĴиде
    -0.17
    POSITIVE LOGITS
    åĮĹ京æŶéĹ´
    0.22
    说å®Į
    0.21
    archical
    0.19
    æŀŃ
    0.19
    èĮ¬
    0.19
    -prepend
    0.19
     Pron
    0.18
    anzi
    0.18
    eroon
    0.18
    elong
    0.18
    Activations Density 0.004%

    No Known Activations