© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 624
    Prev
    Next
    INDEX
    Explanations

    retrograde

    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
     bond
    -0.24
    éĴĴ
    -0.23
    getDefault
    -0.22
     Likes
    -0.22
    ertest
    -0.21
    tré
    -0.21
    ä¸Ŀ
    -0.21
    æĪijå¸ĮæľĽ
    -0.21
    éĢ£çºĮ
    -0.21
     Quad
    -0.20
    POSITIVE LOGITS
    s
    0.27
    们çļĦ
    0.26
    们
    0.25
    便
    0.24
    代表
    0.23
    æIJŃ
    0.23
    åıĤ
    0.23
     fam
    0.23
    brook
    0.22
    累累
    0.22
    Activations Density 0.041%

    No Known Activations