© 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. 12788
    Prev
    Next
    INDEX
    Explanations

    you under

    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
    鹫
    -0.21
    posta
    -0.20
    ·»
    -0.20
    éĥĵ
    -0.19
    åIJĪä½ľåħ±èµ¢
    -0.19
    çļĦç¾İ好
    -0.19
    åĩ¤åĩ°
    -0.18
    示èĮĥåĮº
    -0.18
    ijkl
    -0.18
    çľ¼éĩĮ
    -0.18
    POSITIVE LOGITS
     collapsed
    0.19
    ä¸ĸçķĮ第ä¸Ģ
    0.19
    bib
    0.19
    åIJij社ä¼ļ
    0.18
    akk
    0.18
    (Fl
    0.18
    åĪĿæŃ¥
    0.18
    abo
    0.18
     Fi
    0.17
    顶
    0.17
    Activations Density 0.002%

    No Known Activations