© 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. 51061
    Prev
    Next
    INDEX
    Explanations

    APR Representative

    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
    å¹ķ
    -0.09
    ä¼Ļ
    -0.09
    tain
    -0.09
    entes
    -0.08
    lay
    -0.08
    姿
    -0.08
    åįĬ天
    -0.08
    nier
    -0.08
     cul
    -0.08
    änd
    -0.08
    POSITIVE LOGITS
    ourke
    0.09
    çĵľ
    0.09
    åıªè¦ģæĺ¯
    0.09
     Ferd
    0.09
    æĪijçŁ¥éģĵ
    0.09
    补水
    0.09
     Established
    0.09
    ungi
    0.08
    å®Ĺ
    0.08
    oland
    0.08
    Activations Density 0.002%

    No Known Activations