© 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. 12051
    Prev
    Next
    INDEX
    Explanations

    envy or sucker or fallen or taken

    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
    Stick
    -0.24
    大äºĭ
    -0.19
     Stick
    -0.19
     tamp
    -0.19
     humili
    -0.19
    åľĪåŃIJ
    -0.18
    stick
    -0.18
    äºĭåħ³
    -0.18
    以èī²
    -0.18
    vig
    -0.18
    POSITIVE LOGITS
    å¹³æ°ij
    0.23
    诱人
    0.23
    ä»·ä½į
    0.22
    诱æĥij
    0.22
    欲
    0.21
    å¾ľ
    0.21
    æ°´ä¸Ń
    0.21
     possibilities
    0.21
    åIJijå¾Ģ
    0.20
    å®ŀçī©
    0.20
    Activations Density 0.022%

    No Known Activations