© 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. 16531
    Prev
    Next
    INDEX
    Explanations

    times and dates

    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
    åĪļæīį
    -0.21
    ç¼£
    -0.21
    åĩłå¹´åīį
    -0.21
    æ°¸ä¹ħ
    -0.20
    ael
    -0.20
    åī¥ç¦»
    -0.20
    ream
    -0.20
    è¿ijå¹´æĿ¥
    -0.19
    çĹķ迹
    -0.19
    åįģå¹´åīį
    -0.19
    POSITIVE LOGITS
    esson
    0.20
    ç¿
    0.19
    æģ°
    0.18
    æľı
    0.18
    kü
    0.18
     ChÃŃ
    0.18
    noinspection
    0.17
    xAB
    0.17
    osti
    0.17
    roud
    0.17
    Activations Density 0.020%

    No Known Activations