© 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. 8035
    Prev
    Next
    INDEX
    Explanations

    bring out the best

    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
    åĪĹ为
    -0.09
    çİ¢
    -0.08
    åĪĹ
    -0.08
    éĢĨ
    -0.08
    _imm
    -0.08
    ç½Ĺæĸ¯
    -0.08
    éĴī
    -0.08
    æ³¢çī¹
    -0.08
    åĪĹåħ¥
    -0.08
    ught
    -0.08
    POSITIVE LOGITS
    åħħåĪĨåıijæĮ¥
    0.17
    åıijæĮ¥
    0.16
    åıijæİĺ
    0.15
    çĻ¼æı®
    0.15
    æ½ľèĥ½
    0.14
    æĮĸæİĺ
    0.14
    æıļ
    0.12
    éĩĬæĶ¾
    0.11
    æīįåıijçİ°
    0.11
    åıijæī¬
    0.11
    Activations Density 0.055%

    No Known Activations