© 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. 16927
    Prev
    Next
    INDEX
    Explanations

    background checks

    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
    apolis
    -0.20
    åħį
    -0.20
    å¾µ
    -0.20
    顺çĿĢ
    -0.18
    onaut
    -0.18
    folk
    -0.17
    arat
    -0.17
    绶
    -0.17
    utton
    -0.17
    _Device
    -0.17
    POSITIVE LOGITS
    éľĢè¦ģçĶ¨åĪ°
    0.18
    åİŁæĸĩ
    0.17
    th
    0.17
     Ful
    0.17
    ä¸Ģç¯ĩ
    0.17
     dram
    0.17
    Ìģ
    0.17
     Fam
    0.16
    âİľ
    0.16
    templ
    0.16
    Activations Density 0.001%

    No Known Activations