© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52550
    Prev
    Next
    INDEX
    Explanations

    friend and family relationships

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    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
    ä¸Ī夫
    -0.10
    èijµ
    -0.10
    æĭĶ
    -0.09
     вал
    -0.09
    累累
    -0.09
    ayı
    -0.09
    娶
    -0.09
    æĿĥ
    -0.09
    è´¡
    -0.09
    妻åŃIJ
    -0.09
    POSITIVE LOGITS
    æľĭåıĭ
    0.22
     friends
    0.21
    çļĦæľĭåıĭ
    0.20
    friends
    0.17
     friend
    0.17
     Friends
    0.17
    æľĭåıĭ们
    0.15
    好åıĭ
    0.15
    _friend
    0.15
     FRIEND
    0.14
    Activations Density 0.100%

    No Known Activations