© 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. 61904
    Prev
    Next
    INDEX
    Explanations

    money amounts and life events

    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
    èľĵ
    -0.10
    宵
    -0.09
    çīĮåŃIJ
    -0.09
    ÑĢай
    -0.09
    伤亡
    -0.09
    缴åĪ°
    -0.09
    侧éĿ¢
    -0.09
    没èĥ½
    -0.08
    åĵĵ
    -0.08
     ÑĢей
    -0.08
    POSITIVE LOGITS
    ä¸Ģ次æĢ§
    0.14
    ä¸Ģç¬Ķ
    0.13
    款项
    0.11
    å¥ĸéĩij
    0.10
    继æī¿
    0.10
    éĩijé¢Ŀ
    0.10
    çªģå¦Ĥåħ¶æĿ¥
    0.09
     lump
    0.09
     rede
    0.09
    ä¸ĢæĬ¹
    0.09
    Activations Density 0.067%

    No Known Activations