© 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. 13481
    Prev
    Next
    INDEX
    Explanations

    information status (update, outdated, revision)

    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
    worth
    -0.19
    便åı¯
    -0.18
    é¾Ł
    -0.18
    è¯Ħ审
    -0.17
    osg
    -0.17
    rant
    -0.17
    èŀº
    -0.17
    ìĸ¼
    -0.17
    ible
    -0.17
    æݨåIJij
    -0.17
    POSITIVE LOGITS
    odyn
    0.21
    åĵ¨
    0.20
    è¿Ļåľº
    0.19
    è¿ĻåIJį
    0.19
     Ñıв
    0.19
    icate
    0.19
    æĮĩå®ļ
    0.18
    ãģĿãĤĮãģ¯
    0.18
    è¿Ļ个åIJįåŃĹ
    0.18
    ëĿ¼ëıĦ
    0.17
    Activations Density 0.002%

    No Known Activations