© 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. 200
    Prev
    Next
    INDEX
    Explanations

    Jacuzzi, trojan, kimono, bisexuality

    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
    cri
    -0.24
    人大
    -0.23
    ials
    -0.22
    acia
    -0.22
    ail
    -0.21
    éĢ
    -0.21
    Cri
    -0.21
    ÑģÑĤво
    -0.21
    ated
    -0.21
    è§Ħ
    -0.21
    POSITIVE LOGITS
    0.26
    quo
    0.25
    ãĥ¼
    0.25
    ä»Ģä¹ĪåİŁåĽł
    0.24
     luckily
    0.22
    unks
    0.21
    æŃ£åĽłä¸º
    0.21
    0.21
     Morning
    0.20
     unfortunately
    0.20
    Activations Density 0.134%

    No Known Activations