© 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. 11074
    Prev
    Next
    INDEX
    Explanations

    LinkedIn networking and connections

    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
    rü
    -0.23
    è°ĥæݧ
    -0.22
    åħ¨å¥Ĺ
    -0.22
    æľªæĪIJ年人
    -0.22
    çĶµè§Ĩæľº
    -0.21
    设æĸ½
    -0.20
    ä»£è¡¨åĽ¢
    -0.20
    ream
    -0.20
    éĽĨä½ĵç»ıæµİ
    -0.20
    èķĬ
    -0.19
    POSITIVE LOGITS
     LinkedIn
    0.34
    人èĦī
    0.31
    LinkedIn
    0.30
     Networking
    0.27
    .linkedin
    0.27
     contacts
    0.26
     networking
    0.25
    Networking
    0.25
    èģĮä½į
    0.24
    èģĮåľº
    0.23
    Activations Density 0.028%

    No Known Activations