© 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. 13934
    Prev
    Next
    INDEX
    Explanations

    list delimiters

    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
    以åıĬ
    -0.21
    ades
    -0.19
    èĢĮ对äºİ
    -0.19
    åħħåĪĨä½ĵçİ°
    -0.18
    以åıĬåħ¶ä»ĸ
    -0.18
    åħħåĪĨ
    -0.18
    å¹¶åľ¨
    -0.17
    ìľ¼ë©°
    -0.17
    .tc
    -0.17
    çIJ¬
    -0.17
    POSITIVE LOGITS
    ä½ķå¿ħ
    0.21
    åľ¨ä¹İ
    0.19
    åį´ä¸į
    0.19
    ä¸į代表
    0.19
    olan
    0.19
    راد
    0.18
    ä¸įçIJĨ
    0.18
    ä¿Ŀ驾æĬ¤
    0.18
    åį»
    0.17
    没åħ³ç³»
    0.17
    Activations Density 0.126%

    No Known Activations