© 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. 1819
    Prev
    Next
    INDEX
    Explanations

    web component attributes

    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
     Emer
    -0.25
    主导
    -0.23
     Pert
    -0.23
     Economics
    -0.23
    è¯Ħ为
    -0.23
    -largest
    -0.23
     Fat
    -0.23
    anna
    -0.22
    .Fat
    -0.22
    æ·Ģ
    -0.22
    POSITIVE LOGITS
     correctly
    0.34
     typo
    0.31
     preprocessing
    0.30
     èĭ¥è¦ģ
    0.30
     formatting
    0.29
     syntax
    0.29
    è¿ĻéĩĮ
    0.28
    syntax
    0.28
     setup
    0.28
    è¿Ļåıªæĺ¯
    0.27
    Activations Density 0.364%

    No Known Activations