© 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. 1884
    Prev
    Next
    INDEX
    Explanations

    block parties

    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
    æ®Ĩ
    -0.23
    æ¸łéģĵ
    -0.23
    ä»»ä½ķå½¢å¼ı
    -0.22
    ÑģÑĤв
    -0.20
    äºĭ项
    -0.20
    æľºåľº
    -0.20
    SCREEN
    -0.20
    åŀ¦
    -0.20
    åĽ½åº¦
    -0.20
    ä½ĵ系建设
    -0.20
    POSITIVE LOGITS
    mates
    0.30
    /column
    0.28
    ä¸ĬçļĦ
    0.27
    -level
    0.25
    -wise
    0.25
    -long
    0.24
    -sized
    0.23
     Manhattan
    0.23
    æĪĸå¤ļ
    0.23
     اÙĦÙĪاØŃد
    0.23
    Activations Density 0.018%

    No Known Activations