© 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. 1073
    Prev
    Next
    INDEX
    Explanations

    flash followed by of, Gordon, sale, bomb, .net, load

    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
    ALLY
    -0.20
    çĶŁäº§æĢ»åĢ¼
    -0.19
    ally
    -0.19
    ê¹IJ
    -0.19
    ality
    -0.19
    oplay
    -0.18
    ONY
    -0.18
    egration
    -0.18
     sẵn
    -0.18
    褥
    -0.18
    POSITIVE LOGITS
    lights
    0.28
    light
    0.25
    aney
    0.23
    eries
    0.23
    lint
    0.20
    LIGHT
    0.20
    bear
    0.20
    æ»ĵ
    0.20
    lite
    0.19
    mith
    0.19
    Activations Density 0.012%

    No Known Activations