© 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. 538
    Prev
    Next
    INDEX
    Explanations

    easy to, fluency, electronics, imported

    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
    æĶ¹ä¸º
    -0.24
    aque
    -0.22
     its
    -0.21
     Cape
    -0.21
    mé
    -0.21
    ãģ¨ãģĦãģĨãĤĤãģ®
    -0.21
    igo
    -0.21
    -East
    -0.20
    setDefault
    -0.20
    åĽłä¸ºå®ĥ
    -0.20
    POSITIVE LOGITS
     respectively
    0.34
    å®ĥ们
    0.33
    åīįèĢħ
    0.33
     alike
    0.33
    è¿ĻäºĽéĥ½æĺ¯
    0.33
    åIJĦèĩªçļĦ
    0.27
    ãģĵãĤĮãĤī
    0.26
    è¿ĻäºĽä¸ľè¥¿
    0.26
    ä»ĸ们æĺ¯
    0.26
    俱
    0.26
    Activations Density 1.474%

    No Known Activations