© 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. 11130
    Prev
    Next
    INDEX
    Explanations

    crafted / craftsmanship / crafting

    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
    sWith
    -0.17
    åĮĸèĤ¥
    -0.17
    anness
    -0.17
    ish
    -0.16
    è¿Ļæĺ¯ä¸Ģç§į
    -0.16
    arpa
    -0.16
    å¯Ĥå¯ŀ
    -0.16
    isser
    -0.16
     thoại
    -0.16
    ese
    -0.16
    POSITIVE LOGITS
    èĢĮæĪIJ
    0.26
    åĩºæĿ¥çļĦ
    0.20
    ating
    0.20
    å°ıå¿ĥ
    0.19
    -made
    0.19
     Ñģебе
    0.19
    ä¼ĺç¾İ
    0.19
    ä¸Ģåī¯
    0.17
    ells
    0.17
    ä¸Ģæŀļ
    0.16
    Activations Density 0.026%

    No Known Activations