© 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. 12656
    Prev
    Next
    INDEX
    Explanations

    ISO certifications and standards

    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
    BOSE
    -0.22
    失è°ĥ
    -0.19
    oso
    -0.19
    osal
    -0.19
    æ¦ľ
    -0.19
    é¢Ĩä¼ļ
    -0.19
    boxes
    -0.18
    ÙħصاÙĦØŃ
    -0.18
     Mash
    -0.18
    ä¸įåĩºæĿ¥
    -0.18
    POSITIVE LOGITS
    çŃīå¤ļ项
    0.25
    çŃīå¤ļç§į
    0.24
    åįģå¤ļå¹´
    0.22
    åIJĦ项
    0.21
    å¤ļ项
    0.21
    çŃī诸å¤ļ
    0.21
    å¤ļç§į
    0.19
    å¤ļ家
    0.19
    å¤ļå¹´çļĦ
    0.19
    é«ĺæłĩåĩĨ
    0.19
    Activations Density 0.006%

    No Known Activations