© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 17138
    Prev
    Next
    INDEX
    Explanations

    kids activities and events

    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
    女åıĭ
    -0.09
    ç»ĿæľĽ
    -0.09
     scen
    -0.09
    æĺ§
    -0.08
    人æĢ§
    -0.08
    ä¼ī
    -0.08
    å©Ĭ
    -0.08
    çĪ±æĥħ
    -0.08
    åIJİ代
    -0.08
    uffer
    -0.08
    POSITIVE LOGITS
    éķ¿å¤§äºĨ
    0.13
    åıĶåıĶ
    0.13
    çĪ¸çĪ¸å¦Īå¦Ī
    0.12
    让åŃ©åŃIJ
    0.12
    ä¸Ģ年级
    0.11
    çļĦåŃ©åŃIJ
    0.11
    家éķ¿
    0.11
    æĩĤäºĭ
    0.11
    èĮģ
    0.10
     Kids
    0.10
    Activations Density 0.297%

    No Known Activations