© 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. 727
    Prev
    Next
    INDEX
    Explanations

    data services and communication

    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
     Surround
    -0.25
     Wooden
    -0.24
    æ°¡
    -0.23
    æ¢ĵ
    -0.23
    /process
    -0.23
     unlucky
    -0.23
     consolid
    -0.23
    èĩĮ
    -0.22
    -parts
    -0.22
    ä¸Ģ个好çļĦ
    -0.22
    POSITIVE LOGITS
     traffic
    0.28
    交éĢļ
    0.26
    éĢļä¿¡
    0.26
    俱
    0.26
    åĽ¾æĸĩ
    0.26
     speeds
    0.26
    ç½ij绾
    0.25
    车èģĶç½ij
    0.25
    /tcp
    0.25
    ะ
    0.25
    Activations Density 0.033%

    No Known Activations