© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 12
    Prev
    Next
    INDEX
    Explanations

    pictures of

    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
     mus
    -0.23
    ä¸ĩåı°
    -0.23
    æĶ¾å¼ĥ
    -0.23
    ise
    -0.23
    ä¸įå®ī
    -0.21
    棼
    -0.21
     Mus
    -0.21
    premium
    -0.21
    主
    -0.21
    ISE
    -0.21
    POSITIVE LOGITS
    æĭįçħ§
    0.42
    çħ§çīĩ
    0.35
    /photo
    0.35
    æķ°çłģ
    0.34
    ðŁĵ·
    0.31
     chụp
    0.31
    /print
    0.31
    /video
    0.30
    ðŁĵ¸
    0.30
     camera
    0.30
    Activations Density 0.024%

    No Known Activations