© 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. 55545
    Prev
    Next
    INDEX
    Explanations

    sports team statistics

    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
    é¾
    -0.10
     Juda
    -0.10
    è¿ĽéŨ
    -0.10
    èĩ´çĻĮ
    -0.09
     Seasons
    -0.09
    æµĶ
    -0.09
    å§ĭç»Īä¿ĿæĮģ
    -0.09
    ä»İ严
    -0.08
    åĩºåı°
    -0.08
    udas
    -0.08
    POSITIVE LOGITS
    åıĤåĬł
    0.12
     Chall
    0.09
    被èªī
    0.09
    åıĥåĬł
    0.08
    åıĤä¸İ
    0.08
    对æĬĹ
    0.08
    .fun
    0.08
    æĺŁåħī
    0.08
    çľ©
    0.08
    åIJĦçľģ
    0.08
    Activations Density 0.057%

    No Known Activations