© 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. 2771
    Prev
    Next
    INDEX
    Explanations

    password recovery

    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
    ainen
    -0.23
    çļĦä¸įåIJĮ
    -0.23
    builtin
    -0.23
    æºIJæºIJä¸įæĸŃ
    -0.23
    .enqueue
    -0.22
    æľīè¶³å¤ŁçļĦ
    -0.22
     getArguments
    -0.21
    thro
    -0.21
     (!((
    -0.21
    æľĢä¼ĺ
    -0.20
    POSITIVE LOGITS
    æĢ§åij½
    0.29
     Verse
    0.26
    æľ¬ç«Ļ
    0.23
    å°ı游æĪı
    0.23
     recieved
    0.23
    ä¸İæŶ
    0.22
    éŨæĪ·
    0.22
    icates
    0.22
     Pok
    0.22
    .datab
    0.22
    Activations Density 0.001%

    No Known Activations