© 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. 1752
    Prev
    Next
    INDEX
    Explanations

    information and knowledge sharing

    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
    erval
    -0.26
    igar
    -0.24
    à¹Ĥย
    -0.23
    alte
    -0.23
    åħ¥ä½ı
    -0.23
    kick
    -0.21
    mma
    -0.21
     зÑĢ
    -0.21
    aign
    -0.21
    $__
    -0.21
    POSITIVE LOGITS
    ä¼łæİĪ
    0.35
    çŁ¥è¯Ĩ
    0.33
    çŁ¥èŃĺ
    0.28
    çļĦçŁ¥è¯Ĩ
    0.28
     knowledge
    0.27
    社ä¼ļç§ijåѦ
    0.26
    .answer
    0.26
    ç§ijåѦæĬĢæľ¯
    0.25
    çݰ代社ä¼ļ
    0.25
    çĻ¾ç§ij
    0.25
    Activations Density 0.027%

    No Known Activations