© 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. 12980
    Prev
    Next
    INDEX
    Explanations

    academic subjects

    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
    人æµģ
    -0.19
    çªĦ
    -0.19
    ling
    -0.19
    isy
    -0.18
    ally
    -0.18
    ç®ĢåİĨ
    -0.18
    ãģıãĤĮ
    -0.18
    级åĪ«çļĦ
    -0.17
     consult
    -0.17
    ilage
    -0.17
    POSITIVE LOGITS
    çŁ¥è¯Ĩ
    0.23
    èĥĻ
    0.22
    课
    0.22
    sink
    0.21
    课ç¨ĭ
    0.21
    обÑīа
    0.20
    æ¸Ĭ
    0.20
    ç±»
    0.19
    æĸ¹éĿ¢
    0.19
    .simps
    0.18
    Activations Density 0.024%

    No Known Activations