© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 2147
    Prev
    Next
    INDEX
    Explanations

    company products and services

    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
    ront
    -0.25
    volatile
    -0.24
    éĩijèī²
    -0.23
    ç»ĵæŀĦæĢ§
    -0.23
    typeid
    -0.23
    WithError
    -0.22
     resembl
    -0.22
    TestMethod
    -0.22
    .Spec
    -0.22
    éĺµéĺµ
    -0.21
    POSITIVE LOGITS
     everything
    0.34
    çļĦä¸ĢåĪĩ
    0.34
    å¼ı
    0.33
    everything
    0.31
     Everything
    0.31
    ä¸ĢåĪĩ
    0.29
     suite
    0.28
    ä¸ĢåĪĩéĥ½æĺ¯
    0.28
    ä¸Ģç³»åĪĹ
    0.28
    åIJĦ项
    0.27
    Activations Density 0.053%

    No Known Activations