© 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. 8711
    Prev
    Next
    INDEX
    Explanations

    keep informed or posted

    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
     Leap
    -0.10
    éĽ¢
    -0.09
    åįĩ
    -0.09
    离
    -0.09
    åĮºåĨħ
    -0.08
    人å±ħ
    -0.08
    åĴĮ个人
    -0.08
    èĪģ
    -0.08
    åĢĻ
    -0.08
    æݧ
    -0.08
    POSITIVE LOGITS
    çŁ¥æĥħ
    0.15
    веÑī
    0.11
    éĢļæĬ¥
    0.11
     informed
    0.11
    éĢıæĺİ
    0.10
    åijĬçŁ¥
    0.10
    çŀĴ
    0.10
    款
    0.10
    å®ŀäºĭæ±Ĥæĺ¯
    0.10
    çŁ¥æĻĵ
    0.09
    Activations Density 0.077%

    No Known Activations