© 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. 16134
    Prev
    Next
    INDEX
    Explanations

    autopsy lung pathology specimens

    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
    å¾®å¦Ļ
    -0.22
    AREN
    -0.21
    USH
    -0.21
    .appspot
    -0.21
    车ä½į
    -0.20
    ENSOR
    -0.20
    rollo
    -0.20
    篱
    -0.19
    æĮº
    -0.19
    ester
    -0.18
    POSITIVE LOGITS
    åıĸåĩº
    0.29
    å®ŀçī©
    0.26
    æ£Ģ
    0.25
     inspected
    0.22
    æĬ½æŁ¥
    0.22
    æĭ¿åĩº
    0.21
     specimens
    0.21
    åIJĮå¿ĥ
    0.21
     salv
    0.21
     carc
    0.21
    Activations Density 0.712%

    No Known Activations