© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 1089
    Prev
    Next
    INDEX
    Explanations

    happy or pleased

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    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
    åĬĽéĩı
    -0.30
    clinic
    -0.23
    å§ĭäºİ
    -0.22
    embr
    -0.21
    /from
    -0.21
    注å®ļ
    -0.21
    ä¼Ĺå¤ļ
    -0.20
    å¿ĥå¾Ĺ
    -0.20
    è±
    -0.20
    TM
    -0.20
    POSITIVE LOGITS
    ä»ĸ们éĥ½
    0.23
     overall
    0.22
     rằng
    0.22
     fou
    0.21
    ä¹ĭä½Ļ
    0.21
    íŀĪ
    0.21
    -hot
    0.21
     spit
    0.21
    è¿Ļä¹Īåģļ
    0.20
     StringUtil
    0.20
    Activations Density 0.017%

    No Known Activations