© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 61770
    Prev
    Next
    INDEX
    Explanations

    for a contest or competition

    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
    udas
    -0.09
    æİ¥èijĹ
    -0.09
     Äijám
    -0.09
    羸
    -0.09
    åĪ°åľº
    -0.09
    ãĤĤãĤīãģĪ
    -0.08
    æŁIJä¸Ģ
    -0.08
     traff
    -0.08
    å¾Īæĥ³
    -0.08
     usted
    -0.08
    POSITIVE LOGITS
     Medina
    0.11
    -webpack
    0.10
    ä¸ºæľŁ
    0.09
    åĨ»ç»ĵ
    0.09
    çľĭä»ĸ
    0.09
    éļıæŶéļıåľ°
    0.09
    ä¸Ģç³»åĪĹ
    0.09
     predecessors
    0.08
    æĻºèĥ½åĮĸ
    0.08
    导读
    0.08
    Activations Density 0.055%

    No Known Activations