© 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. 20594
    Prev
    Next
    INDEX
    Explanations

    filename/filetype extensions

    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¸įäºĨ
    -0.12
    éĹ®æĪij
    -0.10
    abb
    -0.09
    xE
    -0.08
    æĭ¼åij½
    -0.08
    åħ¥åħļ
    -0.08
    abouts
    -0.08
    å¾Ĺå¤ļ
    -0.08
    ä»İæł¹æľ¬
    -0.08
    athers
    -0.08
    POSITIVE LOGITS
    timeofday
    0.08
    nano
    0.08
    ature
    0.08
    å¿ħè¦ģçļĦ
    0.08
    åĪ«çļĦ
    0.08
    æ³Ķ
    0.08
    ãģĭãģĭãĤĬ
    0.08
    룩
    0.08
    追
    0.08
    wie
    0.07
    Activations Density 0.241%

    No Known Activations