© 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. 52094
    Prev
    Next
    INDEX
    Explanations

    deserved, earned, rightful

    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
    çī¹è´¨
    -0.09
    èĻ¢
    -0.09
    åĭł
    -0.08
    iscrimination
    -0.08
    æºĺ
    -0.08
    éĽĦåİļ
    -0.08
    ä¸ī代
    -0.08
    çļĦ说æ³ķ
    -0.08
    éĻ¤å¤ķ
    -0.08
    泯
    -0.08
    POSITIVE LOGITS
    çıł
    0.10
    รา
    0.09
    ç»Ń
    0.09
    æĶĺ
    0.09
    ائÙĨ
    0.09
    绩
    0.09
    fully
    0.09
    çºĮ
    0.08
    aad
    0.08
    ç³Ł
    0.08
    Activations Density 0.006%

    No Known Activations