© 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. 7398
    Prev
    Next
    INDEX
    Explanations

    installation or measurement

    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
    çī¹çĤ¹
    -0.10
    çļĦçī¹çĤ¹
    -0.10
    磫
    -0.09
    çī¹çĤ¹æĺ¯
    -0.09
     pardon
    -0.09
    ALSE
    -0.09
    _TB
    -0.09
    ä¼ijéĹ²
    -0.09
    庥
    -0.09
    缴éĢļ车
    -0.08
    POSITIVE LOGITS
    æݪæĸ½
    0.14
    æĻ®åıĬ
    0.11
    åĪ°ä½į
    0.10
    è¦ĨçĽĸçİĩ
    0.10
     measures
    0.10
    -equipped
    0.09
    é½IJåħ¨
    0.09
    zig
    0.09
    æľºåĪ¶
    0.09
    æĦıè¯Ĩ
    0.09
    Activations Density 0.193%

    No Known Activations