© 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. 2590
    Prev
    Next
    INDEX
    Explanations

    leaf litter, weeds, barks, organic matter

    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
    åĩºåĽ½
    -0.26
    é¹Ĺ
    -0.26
    å¤Ķ
    -0.23
    REAM
    -0.23
    IsNull
    -0.23
    弩
    -0.23
    å¼ºåĽ½
    -0.23
    -country
    -0.23
     mainland
    -0.22
    .json
    -0.22
    POSITIVE LOGITS
    è¦ĨçĽĸçİĩ
    0.34
    ä¿Ŀ湿
    0.33
    ä¿Ŀ温
    0.33
    åŀ«
    0.32
    å±Ĥ
    0.30
    è¦ĨçĽĸ
    0.30
     cover
    0.29
    æ¤į被
    0.28
     layer
    0.28
     Hort
    0.28
    Activations Density 0.005%

    No Known Activations