© 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. 7521
    Prev
    Next
    INDEX
    Explanations

    directions identifying places and peoples

    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
    éĢµ
    -0.09
    ITE
    -0.09
     jal
    -0.09
    athed
    -0.09
     cuffs
    -0.09
    amespace
    -0.08
    æªĶ
    -0.08
    ipping
    -0.08
    éĤĽ
    -0.08
    ScrollView
    -0.08
    POSITIVE LOGITS
    人çĶŁçļĦ
    0.10
    å·¥ä½ľçļĦ
    0.10
    fuse
    0.10
    âĢij
    0.10
    ä½łå¥½
    0.09
    éŨå¤ĸ
    0.09
    åĪĽå»ºå·¥ä½ľ
    0.09
    ãģĦãģ¾ãģĻãģĮ
    0.09
     riêng
    0.09
    ç
    0.09
    Activations Density 0.065%

    No Known Activations