© 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. 661
    Prev
    Next
    INDEX
    Explanations

    prevalence percentage

    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
    iese
    -0.25
     tumble
    -0.24
     Votes
    -0.24
     senses
    -0.24
    æľĢå°ij
    -0.23
    rese
    -0.22
    /info
    -0.22
    è³ĩè¨Ĭ
    -0.22
    è´Ń票
    -0.22
    dif
    -0.22
    POSITIVE LOGITS
    æ¯Ķä¾ĭ
    0.29
    çļĦæ¯Ķä¾ĭ
    0.28
    ä¸Ģå°ı
    0.27
    tiny
    0.25
    å¾Īå°ı
    0.25
    ä¸ĩåĪĨ
    0.24
     proportion
    0.24
    æ¯Ķçİĩ
    0.23
    ish
    0.23
    bird
    0.22
    Activations Density 0.202%

    No Known Activations