© 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. 50154
    Prev
    Next
    INDEX
    Explanations

    NYC locations

    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
    çľģåĨħ
    -0.11
    åĨ²
    -0.10
    å´¤
    -0.10
    ä¸įå¤ļ
    -0.10
    æĹłæīĢ
    -0.10
    èį¥
    -0.09
    åĽĽå·Ŀçľģ
    -0.09
    åIJĦçľģ
    -0.09
    çķ
    -0.09
    æĢł
    -0.09
    POSITIVE LOGITS
    纽约
    0.20
     NYC
    0.19
     Bronx
    0.17
     Brooklyn
    0.16
     NYPD
    0.16
    åĮĹ京å¸Ĥ
    0.16
    åľ¨åĮĹ京
    0.13
     Manhattan
    0.13
     Harlem
    0.13
    åĮĹ京
    0.13
    Activations Density 0.208%

    No Known Activations