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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 620
    Prev
    Next
    INDEX
    Explanations

    programming constructs

    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
    ynet
    -0.27
    Bubble
    -0.25
     Bubble
    -0.25
    vert
    -0.23
     propTypes
    -0.23
    TableCell
    -0.23
    ped
    -0.23
    itemId
    -0.22
    ping
    -0.22
    /embed
    -0.21
    POSITIVE LOGITS
     Pavilion
    0.25
     carnival
    0.24
    ÑĢаз
    0.24
    çĶ¨èĩªå·±çļĦ
    0.23
     Ram
    0.23
    conde
    0.23
    åİŁåĪĻ
    0.22
    enco
    0.22
     mad
    0.21
    thumbs
    0.21
    Activations Density 0.009%

    No Known Activations