© 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. 10837
    Prev
    Next
    INDEX
    Explanations

    proper nouns and titles

    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
    é²Ń
    -0.20
    æ§İ
    -0.20
    lashes
    -0.19
    åĨ¢
    -0.19
    æĬķ产
    -0.19
    esc
    -0.19
    astle
    -0.19
    ä½İåİĭ
    -0.18
    éĽī
    -0.18
    <Map
    -0.18
    POSITIVE LOGITS
    主å¸Ń
    0.20
    åIJ¬
    0.20
    reme
    0.20
    view
    0.20
     Burl
    0.19
    PLY
    0.19
     Petro
    0.19
     tert
    0.19
     Ard
    0.19
    èģ½
    0.19
    Activations Density 0.006%

    No Known Activations