© 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. 50965
    Prev
    Next
    INDEX
    Explanations

    signs and what they say

    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
    ãĥģãĥ³
    -0.10
    ายà¸Ļ
    -0.09
    ardo
    -0.09
    adero
    -0.09
    flate
    -0.09
    åĨľä½ľçī©
    -0.09
    ç»ī
    -0.09
    ãĤ«ãĥĥãĥĹ
    -0.09
    æĢģ
    -0.08
    tings
    -0.08
    POSITIVE LOGITS
     thức
    0.10
    åĿĬ
    0.09
    itters
    0.09
    holders
    0.08
    æł·çļĦ
    0.08
    makers
    0.08
    oram
    0.08
    åĪ¶éĢłåķĨ
    0.08
    ÄĽ
    0.08
    ÑģоÑĢ
    0.08
    Activations Density 0.009%

    No Known Activations