© 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. 16596
    Prev
    Next
    INDEX
    Explanations

    start of noun phrases

    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
    OrCreate
    -0.21
    éĢ®
    -0.21
    ities
    -0.19
    Ult
    -0.18
    nes
    -0.18
    åĬłå¿«å»ºè®¾
    -0.18
    å¦Ĥä½ķçľĭå¾ħ
    -0.17
     необÑħодимоÑģÑĤи
    -0.17
     tên
    -0.17
     probable
    -0.16
    POSITIVE LOGITS
    å¾ģç¨ĭ
    0.24
    swith
    0.23
    nings
    0.23
    æĸ°å¾ģç¨ĭ
    0.22
    sWith
    0.21
     обÑĥÑĩениÑı
    0.20
    æĢı
    0.19
     trails
    0.19
     journey
    0.19
     discussions
    0.19
    Activations Density 0.039%

    No Known Activations