© 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. 8752
    Prev
    Next
    INDEX
    Explanations

    Florida coach or institute

    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
    çĦ¶æĺ¯
    -0.12
    åļİ
    -0.11
    edly
    -0.10
    们
    -0.10
    inue
    -0.10
    大楼
    -0.09
    ding
    -0.09
    åĴĮåľ°åĮº
    -0.09
    orem
    -0.09
    éķIJ
    -0.09
    POSITIVE LOGITS
    ç¤ģ
    0.10
    chip
    0.09
    ä¸ĢèĤ¡
    0.09
    ignum
    0.09
    ike
    0.09
    aption
    0.09
    anse
    0.09
    usercontent
    0.09
    ettes
    0.09
    animate
    0.09
    Activations Density 0.007%

    No Known Activations