© 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. 14259
    Prev
    Next
    INDEX
    Explanations

    thunderstorms

    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
    ertest
    -0.21
    ippet
    -0.21
    lename
    -0.19
    odox
    -0.19
    _EXTERN
    -0.19
    æķĻ导
    -0.19
    .tm
    -0.19
    ç¾Ĭæ¯Ľ
    -0.18
    .Rel
    -0.18
    ussion
    -0.18
    POSITIVE LOGITS
    æļ´åĬĽ
    0.23
    é£İæļ´
    0.22
    éĽĨ群
    0.21
    æĢ»éĿ¢ç§¯
    0.19
     Fior
    0.19
    è¿Ļåľº
    0.19
    å´©
    0.19
    ive
    0.18
    åĪĨè£Ĥ
    0.18
    ç«ŀéĢī
    0.18
    Activations Density 0.012%

    No Known Activations