© 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. 1266
    Prev
    Next
    INDEX
    Explanations

    half a

    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
    æĽ´åĬł
    -0.24
    æĸ°ãģŁ
    -0.24
    åĴĮå®ĮåĸĦ
    -0.24
    ucc
    -0.23
    éĢ²ä¸ĢæŃ¥
    -0.23
    åħ¨ãģ¦
    -0.23
    å¾Īæĺ¯
    -0.23
    som
    -0.23
    ãģĦãģıãģ¤ãģĭ
    -0.23
    actly
    -0.22
    POSITIVE LOGITS
     imaginable
    0.32
    ç²¾åĬĽ
    0.27
    ä»·éĴ±
    0.22
    åĵį
    0.21
     useless
    0.21
     circumference
    0.21
     recurs
    0.21
     amount
    0.20
     size
    0.20
    Slf
    0.20
    Activations Density 0.015%

    No Known Activations