© 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. 1077
    Prev
    Next
    INDEX
    Explanations

    web resources with .css urls

    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
     Gst
    -0.22
     maxValue
    -0.22
     Orleans
    -0.22
    linger
    -0.22
    munition
    -0.21
     обоÑĢ
    -0.21
    (Cs
    -0.20
    arming
    -0.20
    fest
    -0.20
    ussed
    -0.20
    POSITIVE LOGITS
    Bookmark
    0.28
     gh
    0.26
     Bookmark
    0.24
     companion
    0.24
     bookmarks
    0.23
    å·¥åħ·
    0.23
     bookmark
    0.23
     tagging
    0.23
     tips
    0.23
     tree
    0.22
    Activations Density 0.005%

    No Known Activations