© 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. 8394
    Prev
    Next
    INDEX
    Explanations

    Pro Shop, Dynasty show, Summit paint

    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
    epy
    -0.11
     Fern
    -0.08
    abay
    -0.08
     Mellon
    -0.08
     pap
    -0.08
    mel
    -0.08
    pls
    -0.07
    åŃļ
    -0.07
    _permission
    -0.07
     Pap
    -0.07
    POSITIVE LOGITS
    éĽĨåĽ¢èĤ¡ä»½
    0.12
    å¹¢
    0.11
    è°¯
    0.11
    è¿Ļ对äºİ
    0.10
    èĽĨ
    0.10
     Carlson
    0.10
    çĶŁæ´»ä¹łæĥ¯
    0.09
    æĮĿ
    0.09
     chóng
    0.09
    èİ·å¾ĹæĦŁ
    0.09
    Activations Density 0.011%

    No Known Activations