© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 2220
    Prev
    Next
    INDEX
    Explanations

    and followed by professions

    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
    ahoo
    -0.10
    æĮĩæľĽ
    -0.09
    éĶĻäºĨ
    -0.09
    é¹Ħ
    -0.08
    æĵį
    -0.08
    ħ§
    -0.08
    两类
    -0.08
    çĻ¾å®¶
    -0.08
    anza
    -0.08
    央
    -0.08
    POSITIVE LOGITS
    é©»
    0.11
    åIJĮæĹ¶ä¹Łæĺ¯
    0.10
     ×ij×¢×ľ
    0.08
    åįģ足
    0.08
    ìĿ¸ìĿ´
    0.08
    åĪĴåĪĨ
    0.08
    ViewItem
    0.08
    æ´§
    0.08
     Sever
    0.08
    第äºĮ天
    0.08
    Activations Density 0.102%

    No Known Activations