© 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. 16132
    Prev
    Next
    INDEX
    Explanations

    marriage records or certificates

    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
    ALAR
    -0.20
    [prop
    -0.20
    âĵĴ
    -0.19
    åī¯ä¸»å¸Ń
    -0.19
    stalk
    -0.19
     datings
    -0.18
     ìłľíĴĪ
    -0.18
    $core
    -0.18
     anymore
    -0.18
     PTS
    -0.18
    POSITIVE LOGITS
    è®°å½ķ
    0.40
     records
    0.33
    æĪ·ç±į
    0.31
    è¨ĺéĮĦ
    0.31
     Records
    0.30
    åİĨåı²
    0.30
    æ°ijåĽ½
    0.29
    records
    0.29
    æŁ¥æī¾
    0.28
    æĻ®æŁ¥
    0.27
    Activations Density 0.026%

    No Known Activations