© 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. 11689
    Prev
    Next
    INDEX
    Explanations

    engraving, inscription, embossed, etching

    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
    hood
    -0.23
    wolf
    -0.18
    æģ¹
    -0.18
    ðŁı»
    -0.17
    izr
    -0.17
    owers
    -0.17
    ãģįãģ¦
    -0.16
     cÄĥng
    -0.16
    osex
    -0.16
    andr
    -0.16
    POSITIVE LOGITS
    å¾Īæ·±
    0.23
    累累
    0.21
    ree
    0.20
    çIJ¢
    0.20
    etched
    0.19
    å®ĿçŁ³
    0.19
    åĪ»
    0.18
    è½¹
    0.18
    éķĮ
    0.18
    ļ
    0.18
    Activations Density 0.014%

    No Known Activations