© 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. 30926
    Prev
    Next
    INDEX
    Explanations

    immigration and migration

    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
    è¹Ĭ
    -0.10
     glasses
    -0.09
    åŁ
    -0.09
    çķĻç»Ļ
    -0.09
    igator
    -0.09
    æ§Ĭ
    -0.08
    cheid
    -0.08
     Bermuda
    -0.08
    åĨħå¤ĸ
    -0.08
     punches
    -0.08
    POSITIVE LOGITS
    è¿ģ移
    0.14
     influx
    0.13
    移æ°ij
    0.13
     migration
    0.12
    éĢĥ离
    0.12
    éĢĥ
    0.12
    è¿ĽæĿ¥
    0.11
    æ¶Įåħ¥
    0.11
     Migration
    0.11
    çļĦåĪ°æĿ¥
    0.10
    Activations Density 0.110%

    No Known Activations