© 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. 431
    Prev
    Next
    INDEX
    Explanations

    trade or upgrade

    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
    åļ¼
    -0.27
     clans
    -0.24
     clar
    -0.23
    æ¾Ħæ¸ħ
    -0.23
    åħ¨æĸĩ
    -0.23
    äºĭæĥħ
    -0.22
     dialect
    -0.22
    Ĩµ
    -0.22
    æīŃ转
    -0.22
     Ada
    -0.22
    POSITIVE LOGITS
    èĪĬ
    0.33
    æŧ
    0.31
     cũ
    0.30
    æį¢äºĨ
    0.30
    (old
    0.29
    åı¤ãģĦ
    0.29
    	old
    0.29
    conversion
    0.28
    /ref
    0.27
     old
    0.26
    Activations Density 0.004%

    No Known Activations