© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 149
    Prev
    Next
    INDEX
    Explanations

    individualized personalized tailor-made treatments

    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
    æĹłç¼ĺ
    -0.25
    åįıä¼ļä¼ļåijĺ
    -0.24
    (fp
    -0.23
    _associ
    -0.23
    oti
    -0.23
     miscellaneous
    -0.22
    骨干
    -0.22
    /ng
    -0.22
     upstream
    -0.22
     ruin
    -0.21
    POSITIVE LOGITS
    å®ļåĪ¶
    0.50
     tailor
    0.50
     tailored
    0.50
    个æĢ§åĮĸ
    0.49
    个æĢ§
    0.43
     personalized
    0.40
     customized
    0.40
     individual
    0.39
     customization
    0.37
     tail
    0.36
    Activations Density 0.069%

    No Known Activations