© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20219
    Prev
    Next
    INDEX
    Explanations

    powerful

    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
    æĿ¥çļĦ
    -0.10
    大ä¼Ĺ
    -0.10
     ÑģамÑĭе
    -0.09
    好åĿı
    -0.09
    quired
    -0.09
    æģª
    -0.09
    ç¾İ好çĶŁæ´»
    -0.08
    jing
    -0.08
    Ùī
    -0.08
    社ä¼ļåĮĸ
    -0.08
    POSITIVE LOGITS
    ness
    0.18
    lest
    0.13
     enough
    0.12
    æĹłæ¯Ķ
    0.12
    -looking
    0.12
    NESS
    0.11
    ä¸Ķ
    0.11
     mẽ
    0.10
    ly
    0.10
    æľīåĬĽ
    0.10
    Activations Density 0.013%

    No Known Activations