© 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. 50752
    Prev
    Next
    INDEX
    Explanations

    Boston, MA institutions

    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
    æ¸Ŀ
    -0.11
    åij¼åĴĮ浩çī¹
    -0.10
    涪
    -0.10
    èĭĵ
    -0.10
    佤
    -0.09
    åįĹæ²Ļ
    -0.09
     Colorado
    -0.09
    è±ģ
    -0.09
    éĩįåºĨ
    -0.09
    å¤Ķ
    -0.09
    POSITIVE LOGITS
     Massachusetts
    0.23
     Boston
    0.23
    Boston
    0.23
     Maine
    0.17
     Celtics
    0.15
     Harvard
    0.15
    ä¿¡éĺ³
    0.15
    温å·ŀ
    0.14
    å®īå¾½çľģ
    0.14
    åĵĪä½Ľ
    0.14
    Activations Density 0.322%

    No Known Activations