© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37017
    Prev
    Next
    INDEX
    Explanations

    became collapsed

    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
    客æĪ·æıIJä¾Ľ
    -0.11
    å°±æĺ¯è¿Ļæł·
    -0.10
    çĶ¨æĪ·æıIJä¾Ľ
    -0.10
    çī¹çĤ¹æĺ¯
    -0.10
    _via
    -0.09
    缸符
    -0.09
    ointed
    -0.09
     позволиÑĤ
    -0.09
    æ¯Ķè¾ĥé«ĺ
    -0.09
    ioni
    -0.09
    POSITIVE LOGITS
    ä¸įåĨį
    0.13
    失åİ»äºĨ
    0.13
    ä¸įåĨįæĺ¯
    0.13
    æ¶Ī失
    0.12
    ä¸įèĥ½åĨį
    0.12
    æµģ失
    0.12
     become
    0.11
    被åĪĹåħ¥
    0.11
    éĢĢåĩº
    0.10
     becomes
    0.10
    Activations Density 0.235%

    No Known Activations