© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 2305
    Prev
    Next
    INDEX
    Explanations

    money laundering operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    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
    æķĻåŃ¦è´¨éĩı
    -0.31
    ä¸Ģ个好çļĦ
    -0.30
     promot
    -0.28
    è¾ħ导åijĺ
    -0.26
     teaching
    -0.25
    è®¤çľŁåŃ¦ä¹ł
    -0.25
    èĤ²äºº
    -0.25
    çļĦç«ŀäºī
    -0.25
     qualities
    -0.25
     graduating
    -0.25
    POSITIVE LOGITS
    åı¯çĸij
    0.47
    éĩijèŀįæľºæŀĦ
    0.43
    çĬ¯ç½ª
    0.40
    å«Įçĸij
    0.38
     laundering
    0.36
    è¿Ŀæ³ķ
    0.35
    éĩijèŀį
    0.35
     launder
    0.35
    è·¨å¢ĥ
    0.34
    èµĦéĩij
    0.33
    Activations Density 0.030%

    No Known Activations