© 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. 39058
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    è±ĨèħIJ
    -0.09
    èĮİ
    -0.08
    äºĽè®¸
    -0.08
    æĿĢ害
    -0.08
    åѦä¸ļ
    -0.08
    .githubusercontent
    -0.08
    éĶĿ
    -0.08
    干线
    -0.08
    ä»ĭ
    -0.08
     heraus
    -0.08
    POSITIVE LOGITS
    åĬ£
    0.10
    ç©·
    0.10
     поÑģл
    0.10
    éĿ©
    0.09
    è¿Ļ段
    0.09
    MBER
    0.09
    åķĸ
    0.09
    åĿ·
    0.09
    è¿Ļ座
    0.09
    æ©ĩ
    0.09
    Activations Density 0.000%

    No Known Activations