© 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. 18
    Prev
    Next
    INDEX
    Explanations

    network interface configuration

    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
     Pitch
    -0.24
    èĢĥè¯ģ
    -0.23
    lifting
    -0.23
     oko
    -0.23
    迹象
    -0.23
    apot
    -0.23
    ä¹Łè¶ĬæĿ¥è¶Ĭ
    -0.23
    .createElement
    -0.23
    Spin
    -0.23
    çģ¯çģ«
    -0.23
    POSITIVE LOGITS
     ports
    0.33
    vlan
    0.30
     vlan
    0.29
    åĸĩåıŃ
    0.28
     tether
    0.28
    olland
    0.28
    è·ij
    0.28
    (Network
    0.28
     dir
    0.27
     outlets
    0.27
    Activations Density 0.068%

    No Known Activations