© 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. 15621
    Prev
    Next
    INDEX
    Explanations

    family

    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
    çµĦ
    -0.20
    di
    -0.19
    æŶæŶ
    -0.19
    Spy
    -0.19
    dog
    -0.19
    å¸ĥ
    -0.19
    é¼ł
    -0.18
    de
    -0.18
     TO
    -0.18
    um
    -0.18
    POSITIVE LOGITS
    家æĹı
    0.39
    çĪ¶åŃIJ
    0.35
    åħ¨å®¶
    0.34
     family
    0.33
    _family
    0.32
    ä¸Ģ家人
    0.31
     Family
    0.30
    family
    0.29
    Family
    0.28
     FAMILY
    0.28
    Activations Density 0.229%

    No Known Activations