© 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. 20983
    Prev
    Next
    INDEX
    Explanations

    unusual characters replaced

    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
    ä¸įè¦ģåĨį
    -0.10
    åĨįä¹Łä¸į
    -0.09
    æļĤ
    -0.09
    åįĩèµ·
    -0.09
    äºĴ缸
    -0.09
    åģ¶
    -0.08
    æĹħ
    -0.08
    åħ±åIJĮ
    -0.08
    éĢĴ
    -0.08
    书åĨĻ
    -0.08
    POSITIVE LOGITS
    åĪł
    0.11
    åİŁèijĹ
    0.11
    ãĤªãĥªãĤ¸ãĥĬãĥ«
    0.11
    æĶ¹åĬ¨
    0.10
    åĪłéĻ¤
    0.10
    缩çŁŃ
    0.10
     оÑĢигина
    0.10
    åĪª
    0.10
    缩åĩı
    0.10
    å¿łå®ŀ
    0.10
    Activations Density 0.086%

    No Known Activations