© 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. 30243
    Prev
    Next
    INDEX
    Explanations

    our cookies and policies

    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
    uÃŃ
    -0.09
    ä½ļ
    -0.09
    åıĹ害
    -0.08
    éĿ¢çĽ®
    -0.08
    ç¨Ģ缺
    -0.08
    èĬ³
    -0.08
    ä¸Ģ个èģĮä¸ļ
    -0.08
    é«¡
    -0.08
    ạ
    -0.08
    ños
    -0.08
    POSITIVE LOGITS
    大家ä¸Ģèµ·
    0.11
    ASTE
    0.11
    apsed
    0.09
     implicitly
    0.09
     Ars
    0.09
    å½Ĵå±ŀ
    0.09
    å¼ŁåŃIJ
    0.08
    ä»Ļ女
    0.08
    èģĮå·¥
    0.08
    uzzi
    0.08
    Activations Density 0.066%

    No Known Activations