© 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. 13586
    Prev
    Next
    INDEX
    Explanations

    data usage and limits

    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
    çĴŀ
    -0.21
    chant
    -0.19
    ç«ł
    -0.19
    çħŀ
    -0.19
    å¾ħ
    -0.19
    æĢ¥
    -0.19
    ç¿Ł
    -0.19
    etal
    -0.19
    DEX
    -0.18
    apos
    -0.18
    POSITIVE LOGITS
    éĻIJéĩı
    0.22
    容éĩı
    0.22
    女æĺŁ
    0.20
    æĿ¾
    0.20
    æľīéĻIJ
    0.20
    读åIJİ
    0.19
    limit
    0.19
    æŁļ
    0.19
    æ»Ĥ
    0.19
    åĢ¾åIJij
    0.19
    Activations Density 0.010%

    No Known Activations