© 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. 67
    Prev
    Next
    INDEX
    Explanations

    malaria prevention, vaccine, parasite

    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
    iÅŁ
    -0.23
    ness
    -0.20
    mutation
    -0.20
     eccentric
    -0.19
    iquid
    -0.19
    principal
    -0.19
    modes
    -0.19
    tures
    -0.19
     favourable
    -0.19
    die
    -0.19
    POSITIVE LOGITS
    -related
    0.28
    /fire
    0.23
    çļĦåıijçĶŁ
    0.22
    .bd
    0.21
    åĬŀçIJĨ
    0.21
    fy
    0.21
    /AIDS
    0.20
    -esque
    0.20
    eer
    0.20
    ized
    0.20
    Activations Density 0.012%

    No Known Activations