© 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. 16871
    Prev
    Next
    INDEX
    Explanations

    passport and visa

    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¯
    -0.23
    çģ«åĬĽ
    -0.21
     <![
    -0.21
    foreground
    -0.20
    客æĪ¿
    -0.19
    åĸ§
    -0.19
    è¯Ħä»·
    -0.18
    主åĬĽ
    -0.18
    _queryset
    -0.18
    éĺµå®¹
    -0.18
    POSITIVE LOGITS
    åĬŀçIJĨ
    0.40
    身份è¯ģ
    0.38
    æīĭç»Ń
    0.37
    è¯ģ件
    0.37
    æĪ·ç±į
    0.32
    æĪ·åı£
    0.31
    身份
    0.31
    çĻ»è®°
    0.31
    çļĦ身份
    0.31
    æĸĩ书
    0.30
    Activations Density 0.049%

    No Known Activations