© 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. 15299
    Prev
    Next
    INDEX
    Explanations

    image or icon links

    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
    é£İåIJ¹
    -0.24
    éĹ¾
    -0.22
    èŀį
    -0.20
    裤
    -0.19
    妤
    -0.19
    Ñĥг
    -0.19
     BSP
    -0.19
     dispens
    -0.19
    ugs
    -0.18
    _accessible
    -0.18
    POSITIVE LOGITS
    OLVE
    0.21
    æµ·æĬ¥
    0.19
    为åĩĨ
    0.19
    crate
    0.19
    åıĬ缸åħ³
    0.19
     Reload
    0.19
    ToLocal
    0.19
    achi
    0.18
     Seed
    0.17
    Century
    0.17
    Activations Density 0.006%

    No Known Activations