© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 207
    Prev
    Next
    INDEX
    Explanations

    connection, relationship, bond

    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
     Ahead
    -0.24
    åĨ³è®®
    -0.23
    æĬ¼ãģĹ
    -0.23
    ä¼ĺæĥłæĶ¿çŃĸ
    -0.22
    ä¸ĵä¸ļåĮĸ
    -0.22
    æģŃåĸľ
    -0.22
     запиÑģи
    -0.21
    次æķ°
    -0.21
    åĮ¡
    -0.21
    åĨ»ç»ĵ
    -0.21
    POSITIVE LOGITS
     connection
    0.33
    æĽ´æ·±
    0.33
     bond
    0.33
     communic
    0.32
    äºĴåĬ¨
    0.32
     relationship
    0.32
     communion
    0.32
     spirituality
    0.31
    纽带
    0.31
    亲å¯Ĩ
    0.30
    Activations Density 0.050%

    No Known Activations