© 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. 36256
    Prev
    Next
    INDEX
    Explanations

    get something

    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
    aget
    -0.11
    ieu
    -0.11
    èĦĶ
    -0.09
    æĸ¯åŁº
    -0.09
    urrent
    -0.09
    гла
    -0.09
    以åıĬåħ¶ä»ĸ
    -0.09
    GetX
    -0.09
    ç»Ļä½łä»¬
    -0.09
    Pixmap
    -0.09
    POSITIVE LOGITS
     rid
    0.12
    timeofday
    0.10
    åįģ足
    0.10
    ters
    0.10
    tings
    0.09
    éĢŀ
    0.09
    aways
    0.09
     hại
    0.09
    份
    0.08
    æīĭä¸Ń
    0.08
    Activations Density 0.107%

    No Known Activations