© 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. 171
    Prev
    Next
    INDEX
    Explanations

    cross-linking polymers

    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
     divert
    -0.27
     beat
    -0.25
     cris
    -0.25
     criminal
    -0.23
    åķ¼
    -0.23
    èĩªæĿĢ
    -0.23
     Statue
    -0.22
     Dealer
    -0.22
     stacked
    -0.22
    åĬĿ
    -0.22
    POSITIVE LOGITS
    anchor
    0.28
     anchor
    0.28
    Anchor
    0.28
     Anchor
    0.27
     anchors
    0.27
     tails
    0.26
    éĶļ
    0.26
    /link
    0.26
    tie
    0.25
     bonds
    0.24
    Activations Density 0.236%

    No Known Activations