© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37236
    Prev
    Next
    INDEX
    Explanations

    hockey player and team names

    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
    天津å¸Ĥ
    -0.10
    念
    -0.10
    æĭĶ
    -0.10
    è¿·
    -0.09
    æĺ§
    -0.09
    æŁ¥çľĭåħ¨æĸĩ
    -0.08
    åį°
    -0.08
    èijµ
    -0.08
    _LS
    -0.08
    æĭĮ
    -0.08
    POSITIVE LOGITS
     NHL
    0.14
     Hockey
    0.13
    åĬłæĭ¿å¤§
    0.12
    åĬłæĭ¿
    0.12
     hockey
    0.11
     skating
    0.10
    ä¹Įåħĭåħ°
    0.10
    Toronto
    0.09
     Montreal
    0.09
    æĸ¯åŁº
    0.09
    Activations Density 0.210%

    No Known Activations