© 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. 14362
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with symbols

    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»į
    -0.22
     exce
    -0.20
     intercept
    -0.20
    æĭ¦æĪª
    -0.19
    渤
    -0.19
    FIG
    -0.18
    ooter
    -0.18
     bun
    -0.18
     magn
    -0.17
     experienced
    -0.17
    POSITIVE LOGITS
    æĭĦ
    0.18
    ettel
    0.18
    ród
    0.18
    mát
    0.18
    èĩ¾
    0.18
     détail
    0.18
    äºĶå¹´
    0.17
    etten
    0.17
    åĩ¡äºĭ
    0.17
    #ga
    0.17
    Activations Density 0.035%

    No Known Activations