© 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. 27905
    Prev
    Next
    INDEX
    Explanations

    paying back money

    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
    åģ·
    -0.09
    å¤¸å¼ł
    -0.09
    éŨå¤ĸ
    -0.09
    å²
    -0.09
    ERING
    -0.09
    ä»Ģä¹Īåľ°æĸ¹
    -0.09
     ÑģоÑģÑĤ
    -0.09
    åĨįä¸Ģ次
    -0.09
    ply
    -0.09
    é¦ı
    -0.08
    POSITIVE LOGITS
    izin
    0.10
    wards
    0.09
     Horton
    0.09
    å¤Ļ
    0.09
    æĤ©ãģ¿
    0.09
    WARDS
    0.09
    å®Įæ¯ķ
    0.08
    OI
    0.08
    uden
    0.08
    åĨĮ
    0.08
    Activations Density 0.005%

    No Known Activations