© 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. 33190
    Prev
    Next
    INDEX
    Explanations

    past tense verbs and financial transactions

    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
    åľ¨éĩĮéĿ¢
    -0.11
    ×ļ
    -0.09
    追éĹ®
    -0.09
    åĺİ
    -0.09
    æīĢéľĢ
    -0.09
     gul
    -0.09
    æīĵæĸŃ
    -0.09
    赶æĿ¥
    -0.08
    å·²ä¹ħ
    -0.08
    åłĤ
    -0.08
    POSITIVE LOGITS
    åĩºåİ»
    0.13
    ç»ĻåĪ«äºº
    0.13
    åįĸç»Ļ
    0.13
    转让
    0.12
    åĩºåĶ®
    0.12
    ä½ĥ
    0.10
    Posting
    0.09
    à¸Ĥาย
    0.09
    对å¤ĸ
    0.09
    åįĸ
    0.09
    Activations Density 0.069%

    No Known Activations