© 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. 13102
    Prev
    Next
    INDEX
    Explanations

    web development code (.php, .tpl, .css)

    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
    åĸĺ
    -0.19
    oods
    -0.18
    åıĸè¯ģ
    -0.18
    opensource
    -0.18
    榫
    -0.18
     vern
    -0.17
    .connector
    -0.17
    å°Ĭ严
    -0.17
    çľĭæ¸ħ
    -0.17
    æĬ¤èº«ç¬¦
    -0.17
    POSITIVE LOGITS
    å¡«
    0.21
     widgets
    0.20
    ä½įç½®
    0.20
    è¡¿
    0.20
     dereg
    0.20
    rey
    0.19
     POSITION
    0.19
    ãĤ¦ãĤ£
    0.19
    éĺµåľ°
    0.19
    çļĦä½įç½®
    0.18
    Activations Density 0.010%

    No Known Activations