© 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. 36751
    Prev
    Next
    INDEX
    Explanations

    bridge construction

    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
    æijĨåľ¨
    -0.11
    æĺŁçIJĥ
    -0.11
    å°¼äºļ
    -0.08
    åĿĮ
    -0.08
    æĥij
    -0.08
    æĺ§
    -0.08
    tam
    -0.08
    .getLine
    -0.08
    est
    -0.08
    ration
    -0.08
    POSITIVE LOGITS
    åĿĬ
    0.10
    aub
    0.09
    åĢĻ
    0.09
    奥æĸ¯åį¡
    0.09
    è¦ĨçĽĸçİĩ
    0.09
    Basket
    0.08
    SR
    0.08
    .syn
    0.08
    æį·
    0.08
    -sk
    0.08
    Activations Density 0.016%

    No Known Activations