© 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. 4252
    Prev
    Next
    INDEX
    Explanations

    residency or residence

    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
     bÄĥng
    -0.10
     Barcode
    -0.10
    Contracts
    -0.09
    è¿ŁåĪ°
    -0.09
    ABEL
    -0.09
     successors
    -0.09
    èģĬèģĬ
    -0.09
    .experimental
    -0.09
    åIJĦéĥ¨éŨ
    -0.09
    è´´åIJ§
    -0.09
    POSITIVE LOGITS
    åģľçķĻ
    0.11
    身份
    0.11
     residence
    0.11
     residency
    0.11
    ä½ıåľ¨
    0.10
    ä½ıæīĢ
    0.10
    å±ħæ°ij
    0.10
     Residence
    0.10
    å®ļå±ħ
    0.09
    åĪģ
    0.09
    Activations Density 0.060%

    No Known Activations