© 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. 50236
    Prev
    Next
    INDEX
    Explanations

    public transportation stops and information

    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
    å¼Łå¼Ł
    -0.10
    esis
    -0.09
    æľīèĥ½åĬĽ
    -0.09
    å°ıãģķ
    -0.09
    大桥
    -0.09
    åħĦå¼Ł
    -0.09
    èĥľä»»
    -0.08
    åĴĮå°ļ
    -0.08
     Thornton
    -0.08
    ussion
    -0.08
    POSITIVE LOGITS
    åħ¬äº¤
    0.13
     bus
    0.12
     buses
    0.11
    åħ¬äº¤è½¦
    0.10
    bus
    0.10
    åħ¬åħ±äº¤éĢļ
    0.10
     Bus
    0.10
    æľį
    0.09
    /bus
    0.09
    Bus
    0.09
    Activations Density 0.078%

    No Known Activations