© 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. 128
    Prev
    Next
    INDEX
    Explanations

    invasion, raid, attack

    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
    æĮĤçīĮ
    -0.26
     меÑĤÑĢо
    -0.25
     SECRET
    -0.25
    phin
    -0.25
    photos
    -0.25
    åĬŀåħ¬æ¥¼
    -0.25
    rieve
    -0.23
     Cove
    -0.23
    æ¤įçī©
    -0.23
    unlink
    -0.23
    POSITIVE LOGITS
    ä¾µçķ¥
    0.40
    éªijåħµ
    0.37
    åħ¥ä¾µ
    0.37
     invasion
    0.35
     massac
    0.35
    æİł
    0.34
     invaders
    0.34
     unstoppable
    0.34
     rampage
    0.34
     barbar
    0.33
    Activations Density 0.034%

    No Known Activations