© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 282
    Prev
    Next
    INDEX
    Explanations

    credit card fraudulent activities

    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
    åĽłåľ°åĪ¶å®ľ
    -0.30
    åĬ¡å®ŀ
    -0.27
     aficion
    -0.26
     rivalry
    -0.26
     modest
    -0.26
    主è§Ĵ
    -0.25
     imaginative
    -0.25
     thrilling
    -0.25
    çģµæĦŁ
    -0.24
     dazzling
    -0.24
    POSITIVE LOGITS
    éĢ¾æľŁ
    0.43
    注éĶĢ
    0.42
    ä»ĺ款
    0.37
    åĪ°æľŁ
    0.35
     prepaid
    0.32
    è¿Ŀæ³ķ
    0.32
    èIJ¥ä¸ļæī§çħ§
    0.31
    éĢĢåĽŀ
    0.31
    åĽłä¸ºæĪij
    0.30
    éĤ®å¯Ħ
    0.30
    Activations Density 0.047%

    No Known Activations