© 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. 36115
    Prev
    Next
    INDEX
    Explanations

    distance or separation

    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
    essen
    -0.10
    ä¸įæĪIJ
    -0.10
    åij½ä¸Ń
    -0.09
    bsp
    -0.09
    æĶ»åĬ¿
    -0.09
    æ¸ĹéĢı
    -0.09
    大å±Ģ
    -0.08
    æ±¹
    -0.08
    -middle
    -0.08
    åħ¥ä½ı
    -0.08
    POSITIVE LOGITS
    è¿ľç¦»
    0.29
     away
    0.23
    离å¼Ģ
    0.22
    èĦ±ç¦»
    0.20
     Away
    0.20
    Away
    0.18
    离å¼ĢäºĨ
    0.18
    éĽ¢éĸĭ
    0.18
    离
    0.18
    away
    0.18
    Activations Density 0.059%

    No Known Activations