© 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. 1936
    Prev
    Next
    INDEX
    Explanations

    new product releases

    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
     ourselves
    -0.26
     eventually
    -0.25
    ijn
    -0.24
     yourselves
    -0.24
     later
    -0.23
    phis
    -0.23
    è´¨
    -0.23
    åħĪæĬĬ
    -0.23
    éĥ½å°Ĩ
    -0.23
    æķ´ä¸ªäºº
    -0.22
    POSITIVE LOGITS
    ä¸Ģ个æĸ°çļĦ
    0.31
    æĸ°è½¦
    0.29
    åķ¦
    0.26
     hoy
    0.25
     today
    0.25
    è¿ijæĹ¥
    0.24
    æĹ¥åīį
    0.24
    æĺ¨æĹ¥
    0.24
    è¿İæĿ¥äºĨ
    0.23
     inaugural
    0.23
    Activations Density 0.213%

    No Known Activations