© 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. 121
    Prev
    Next
    INDEX
    Explanations

    Greenwood and wood compound words

    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
    aries
    -0.25
    athon
    -0.24
    cher
    -0.23
    æĹ¥åĨħ
    -0.23
    aceous
    -0.23
    æŦ
    -0.23
    ing
    -0.23
    ilian
    -0.23
    elog
    -0.22
    eness
    -0.22
    POSITIVE LOGITS
    tv
    0.25
    /down
    0.23
     lẽ
    0.21
     Airlines
    0.20
    szed
    0.20
    åŀĪ
    0.20
    渰
    0.20
    ITHER
    0.19
    大éģĵ
    0.19
    èĵ¢
    0.19
    Activations Density 0.022%

    No Known Activations