© 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. 2649
    Prev
    Next
    INDEX
    Explanations

    albeit

    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
    大åį«
    -0.25
    æĸ¼
    -0.24
    äºĮæľŁ
    -0.23
    bam
    -0.23
     lap
    -0.23
     Bos
    -0.22
     kindly
    -0.21
    åīľ
    -0.21
    åĿ¤
    -0.21
    $_['
    -0.21
    POSITIVE LOGITS
     namely
    0.30
     nämlich
    0.28
     ведÑĮ
    0.27
    åĵªåĦ¿
    0.24
    ä¿Ĺ称
    0.24
    ometimes
    0.24
    ãģ¤ãģ¾ãĤĬ
    0.23
    either
    0.23
    æĹ¢èĥ½
    0.23
     albeit
    0.22
    Activations Density 0.081%

    No Known Activations