© 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. 9498
    Prev
    Next
    INDEX
    Explanations

    you ... visit/make/have

    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
    éĶģ
    -0.10
    ä½ĵä¼ļ
    -0.09
    .nil
    -0.09
    usal
    -0.09
    Synopsis
    -0.08
    EditMode
    -0.08
    å½»åºķ
    -0.08
    èĪ«
    -0.08
    åĪ»
    -0.08
    èħ¾
    -0.08
    POSITIVE LOGITS
    æħķ
    0.10
    ä¸ľè¥¿
    0.09
    çķ¿
    0.09
     invol
    0.09
    æīĵ交éģĵ
    0.09
    .GetData
    0.09
    åıĤä¸İ
    0.09
    带çĿĢ
    0.09
    御
    0.09
    åľ¨æĪij
    0.09
    Activations Density 0.037%

    No Known Activations