© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 2333
    Prev
    Next
    INDEX
    Explanations

    silent film

    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
    符åIJĪæĿ¡ä»¶
    -0.28
     daģı
    -0.26
    é¥Ń
    -0.26
    Ordered
    -0.25
     Ordered
    -0.25
    åµĮ
    -0.24
    æİī
    -0.24
    è´ª
    -0.23
     ruin
    -0.23
    å¼Ģå±Ģ
    -0.23
    POSITIVE LOGITS
    ä¼łè¾¾
    0.58
     communication
    0.54
     communicating
    0.54
     communicate
    0.53
    æ²ŁéĢļ
    0.51
     communicated
    0.50
    communic
    0.50
     communicates
    0.49
    交æµģ
    0.49
     conveying
    0.47
    Activations Density 0.073%

    No Known Activations