© 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. 369
    Prev
    Next
    INDEX
    Explanations

    wine, beer, spirits

    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
     ÑģпиÑģ
    -0.25
     alien
    -0.25
    deployment
    -0.24
     занÑıÑĤ
    -0.24
     shopping
    -0.24
    äºĭä¸ļåįķä½į
    -0.24
    æ±ĤåĬ©
    -0.23
     ÑĢабоÑĤник
    -0.23
    edian
    -0.23
     actor
    -0.23
    POSITIVE LOGITS
    åĵģè´¨
    0.36
     produced
    0.31
    æĪIJåĵģ
    0.30
    产éĩı
    0.30
    åĵģ質
    0.30
    纯åĩĢ
    0.29
    纯
    0.28
    istrict
    0.28
     quality
    0.28
    é«ĺåĵģè´¨
    0.28
    Activations Density 0.024%

    No Known Activations