© 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. 62425
    Prev
    Next
    INDEX
    Explanations

    become to

    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
    åħĭæĸ¯
    -0.10
    agara
    -0.09
    鸳
    -0.08
    çļĦçľĭæ³ķ
    -0.08
    lias
    -0.08
    lier
    -0.08
     inex
    -0.08
    èĩªæĿ¥
    -0.08
    ãģĭãģĦ
    -0.08
    .toInt
    -0.08
    POSITIVE LOGITS
     Mouth
    0.10
    achten
    0.10
    毫æĹłçĸijéĹ®
    0.10
    åĮĸçŁ³
    0.10
    åħ·æľīä¸Ģå®ļ
    0.10
     Traverse
    0.09
    æ³ł
    0.09
    iment
    0.09
    å¼
    0.09
     Succ
    0.09
    Activations Density 0.079%

    No Known Activations