© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9975
    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
    寡
    -0.10
    ä¸ĢæŃ¥
    -0.10
    åı£ä¸Ń
    -0.09
    ç»ĦåĽ¾
    -0.09
    çŀİ
    -0.09
     Step
    -0.09
     poorly
    -0.08
    对æłĩ
    -0.08
    æľĢåħĪ
    -0.08
     gj
    -0.08
    POSITIVE LOGITS
    ä»·ä½į
    0.10
    èĪ¬çļĦ
    0.10
    çĨŁæĤīçļĦ
    0.10
     amount
    0.10
    ëĮĢë¡ľ
    0.09
     levels
    0.09
    ä»·
    0.09
    æŶéĹ´åĨħ
    0.09
    è·Ŀ离
    0.09
     ÑĥÑĢовне
    0.09
    Activations Density 0.213%

    No Known Activations