© 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. 8252
    Prev
    Next
    INDEX
    Explanations

    Lamar, Mar, Mark

    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
    ADS
    -0.09
    teen
    -0.09
    å¤ĸèµĦ
    -0.09
    笥
    -0.09
    ÙĪاء
    -0.08
    SourceType
    -0.08
    马åĬĽ
    -0.08
    LayoutConstraint
    -0.08
    åıī
    -0.08
    roys
    -0.08
    POSITIVE LOGITS
    æĥħ
    0.10
    è¯ģåĪ¸æĬķèµĦ
    0.09
    éļ¾åħ³
    0.08
    rot
    0.08
    æīĢæľī人
    0.08
    unread
    0.08
     вÑģем
    0.08
     ayr
    0.08
    vier
    0.08
     reign
    0.08
    Activations Density 0.007%

    No Known Activations