© 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. 12193
    Prev
    Next
    INDEX
    Explanations

    requesting more information

    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
    åĪĽéĢłåĬĽ
    -0.19
    èĢĮæĪIJ
    -0.19
    tips
    -0.19
     دÙĪر
    -0.19
     Vic
    -0.19
    ÙĩÙĨ
    -0.19
    åĩłå®¶
    -0.18
     dov
    -0.18
    CallCheck
    -0.18
    äºĨ许å¤ļ
    -0.18
    POSITIVE LOGITS
    åħ·ä½ĵ
    0.23
    åħ·ä½ĵçļĦ
    0.21
    以便
    0.20
    æ¸ħæ¥ļ
    0.20
    æĺİç¡®
    0.19
    lena
    0.19
    ä¸Ģ个éĹ®é¢ĺ
    0.19
    æĸĩä½ĵ
    0.19
    好åIJĹ
    0.19
    太å°ij
    0.19
    Activations Density 0.030%

    No Known Activations