© 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. 3344
    Prev
    Next
    INDEX
    Explanations

    game titles and software

    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
    æĽ³
    -0.10
    å½ĵåľº
    -0.09
    ä½ľåĵģåĨħ容
    -0.09
    æ¸ħæ´ģ
    -0.09
    侬
    -0.09
    uda
    -0.09
    ÑijÑĢ
    -0.09
    ç°¸
    -0.09
    夷
    -0.09
    ç§ijåѦæĬĢæľ¯
    -0.09
    POSITIVE LOGITS
    à¸Ĥà¸Ļ
    0.10
    ensions
    0.09
    峡谷
    0.08
    .utilities
    0.08
    ä¼ı
    0.08
    çIJ¨
    0.08
    æľĪèĸª
    0.08
    dk
    0.08
     Rak
    0.08
    éĶ²
    0.08
    Activations Density 0.012%

    No Known Activations