© 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. 1378
    Prev
    Next
    INDEX
    Explanations

    bring something or someone

    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
    burgh
    -0.24
    eson
    -0.23
    ë¹ł
    -0.22
    ICE
    -0.21
    æŀIJ
    -0.21
     preferring
    -0.21
    çľ¼åīį
    -0.21
    -corner
    -0.21
    ãģ¹
    -0.21
    LOC
    -0.20
    POSITIVE LOGITS
    æIJºå¸¦
    0.34
    è¡ĮæĿİ
    0.28
    åĽŀæĿ¥
    0.27
     companion
    0.26
    ä¼´ä¾£
    0.25
    å®łçī©
    0.25
    /import
    0.25
    ä»Ģä¹Īéĥ½
    0.24
     accompanying
    0.23
    客人
    0.23
    Activations Density 0.019%

    No Known Activations