© 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. 14092
    Prev
    Next
    INDEX
    Explanations

    please do not

    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
    äºĮèĢħ
    -0.24
    åīįèĢħ
    -0.21
     даж
    -0.19
    两èĢħ
    -0.19
    ä»»æľŁ
    -0.19
    è¿Ļåı¥è¯Ŀ
    -0.19
    èĦ±
    -0.19
    dn
    -0.19
    à¸Ńà¸Ń
    -0.18
    Combo
    -0.18
    POSITIVE LOGITS
    å°±è¿Ļæł·
    0.23
     дов
    0.20
    åķ°
    0.20
    è°¨
    0.19
    éĵ¢
    0.19
    åIJ¬å®Į
    0.19
    çĪ±ç¾İ
    0.18
    è°Ĩ
    0.18
    æĶ¥
    0.18
     Sponsored
    0.18
    Activations Density 0.027%

    No Known Activations