© 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. 13773
    Prev
    Next
    INDEX
    Explanations

    URLs and web addresses

    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
    åĪ©çī©
    -0.24
     Squad
    -0.20
    ä¸įçŁ¥ä¸į
    -0.20
    ãĤ³ãĥ¼ãĥ
    -0.20
    LPARAM
    -0.20
    éľĨ
    -0.19
    åįķåħĥ
    -0.18
    asjon
    -0.18
    éĹ´æİ¥
    -0.18
     sniper
    -0.18
    POSITIVE LOGITS
    ergy
    0.18
    setDisplay
    0.18
    Õº
    0.18
    å¤ļäºĨ
    0.18
    åħ³
    0.18
    {}
    0.18
    íĺķ
    0.18
    imate
    0.17
     vÃŃ
    0.17
     shutdown
    0.17
    Activations Density 0.085%

    No Known Activations