© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15637
    Prev
    Next
    INDEX
    Explanations

    username, password, and credentials

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    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
    æ·¤
    -0.27
    æī¬
    -0.21
    akan
    -0.21
    .LayoutInflater
    -0.19
     ETF
    -0.18
    æĻ¡
    -0.18
     iid
    -0.18
     Sar
    -0.18
    éĿ
    -0.18
    èľĥ
    -0.18
    POSITIVE LOGITS
     security
    0.38
     authentication
    0.37
    çĻ»å½ķ
    0.36
     password
    0.35
    å¯Ĩçłģ
    0.35
    security
    0.34
     passwords
    0.33
     credentials
    0.31
     authorization
    0.31
    身份
    0.31
    Activations Density 0.516%

    No Known Activations