© 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. 15913
    Prev
    Next
    INDEX
    Explanations

    exclamations of surprise or strong emotion

    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
    é¹Ħ
    -0.22
    iele
    -0.21
    åĨ·åĨ·
    -0.21
    ä¸ĢéĿ¢
    -0.20
    éķ¿å®ī
    -0.19
    æ°¸
    -0.19
     Nack
    -0.19
    pton
    -0.19
    笼
    -0.18
    æħ°
    -0.18
    POSITIVE LOGITS
    æķijåij½
    0.19
    éĤ£ä¸ĢåĪ»
    0.18
    aring
    0.18
    inc
    0.17
    gal
    0.17
    deque
    0.17
    xae
    0.17
    ç«ŁçĦ¶
    0.17
    è¿Ļä¸ĢåĪ»
    0.17
    hood
    0.17
    Activations Density 0.007%

    No Known Activations