© 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. 12028
    Prev
    Next
    INDEX
    Explanations

    a good job

    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
    ä¸Ģ个æĸ°çļĦ
    -0.24
    ä¸Ģ个éĹ®é¢ĺ
    -0.21
    æĽ´å¤ļä¿¡æģ¯
    -0.21
    ä¸Ģ種
    -0.20
    ä¸Ģç§į
    -0.20
    åį³å°ĨåĪ°æĿ¥
    -0.18
    æĮĩ导æĦıè§ģ
    -0.17
    æµĵåİļ
    -0.17
    OLER
    -0.17
     dön
    -0.17
    POSITIVE LOGITS
    å¾Ĺå¾Ī
    0.18
    yr
    0.18
    oble
    0.17
    ionario
    0.17
    å®ħ
    0.17
    orman
    0.16
    squ
    0.16
    ÙĪا
    0.16
    MimeType
    0.16
    xygen
    0.16
    Activations Density 0.046%

    No Known Activations