© 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. 14688
    Prev
    Next
    INDEX
    Explanations

    Category names

    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
     Net
    -0.23
     email
    -0.22
    _NET
    -0.21
     offline
    -0.20
     EPS
    -0.19
    æ¶IJ
    -0.18
     parch
    -0.18
     rol
    -0.18
    åij½é¢ĺ
    -0.18
    社ä¼ļåĮĸ
    -0.18
    POSITIVE LOGITS
    .wik
    0.24
     Wikimedia
    0.23
    ä¸ĭéĿ¢æĺ¯å°ı
    0.22
    è¯įæĿ¡
    0.21
    åIJį称
    0.21
    .svg
    0.20
    佩æĪ´
    0.20
    ä¸ī级
    0.20
    åħ¶ä¸Ńä¹ĭä¸Ģ
    0.20
    身é«ĺ
    0.19
    Activations Density 0.229%

    No Known Activations