© 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. 2678
    Prev
    Next
    INDEX
    Explanations

    conference or ACC tournament game

    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
    åĪ»
    -0.10
    稳妥
    -0.10
    åĸĦæĦı
    -0.09
    åĪ¹
    -0.08
    åīĶ
    -0.08
    饥饿
    -0.08
    åĮķ
    -0.08
    æĢ¼
    -0.08
    éĶĢ
    -0.08
    大ä¼ļ
    -0.08
    POSITIVE LOGITS
    çĶŁæľº
    0.10
    åĴĮåľ°åĮº
    0.09
    æĪIJç«ĭ以æĿ¥
    0.09
    æ£ĺ
    0.08
    é£Łçī©
    0.08
    å½ĵåį³
    0.08
     Howell
    0.08
    éĵİ
    0.08
    çĽijçĿ£ç®¡çIJĨ
    0.08
    ä¸Ńæľī
    0.08
    Activations Density 0.012%

    No Known Activations