© 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. 2340
    Prev
    Next
    INDEX
    Explanations

    phishing scams

    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
    antha
    -0.24
    åłĨ
    -0.23
    é¢ł
    -0.23
    OWN
    -0.22
    Josh
    -0.21
    ä½ĵç³»
    -0.20
    host
    -0.20
    Oops
    -0.20
    izzazione
    -0.20
    Collision
    -0.20
    POSITIVE LOGITS
    æ°´éĿ¢
    0.27
    çļĦæĪIJ绩
    0.22
    æ°´ä¸Ń
    0.21
     London
    0.21
     copies
    0.21
    伦æķ¦
    0.21
    红线
    0.21
     Eggs
    0.21
     vign
    0.21
    æĪijä¸Ģ缴
    0.20
    Activations Density 0.003%

    No Known Activations