© 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. 56184
    Prev
    Next
    INDEX
    Explanations

    college sports seasons and titles

    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
     hitch
    -0.09
    -scrollbar
    -0.08
     Erdogan
    -0.08
    è¿Ļå°±
    -0.08
    ritz
    -0.08
    æĶ¾å¤§
    -0.08
     Roths
    -0.08
    æĶ¯
    -0.08
     multis
    -0.08
    ROT
    -0.08
    POSITIVE LOGITS
    ç½ij讯
    0.09
    åĬ³
    0.09
    åĮĹç¾İ
    0.09
    æı©
    0.08
    ç»Ħç»ĩå®ŀæĸ½
    0.08
    çıĬçijļ
    0.08
    é¾Ł
    0.08
    èĵī
    0.08
    澳大åĪ©äºļ
    0.08
    çĶŁåij½åĬĽ
    0.08
    Activations Density 0.116%

    No Known Activations