© 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. 420
    Prev
    Next
    INDEX
    Explanations

    list of categories or types

    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
    dsn
    -0.28
    åīįç½®
    -0.25
    è¿Ļä¸ĢåĪĩ
    -0.24
    æĪIJ为ä¸Ģ个
    -0.23
    Sentence
    -0.23
    ETO
    -0.22
    ä¸ºæľŁ
    -0.22
    eton
    -0.22
    ounder
    -0.22
    illet
    -0.22
    POSITIVE LOGITS
     notable
    0.38
    åĪĹ表
    0.35
     listed
    0.34
    åIJįåįķ
    0.33
     list
    0.33
    listed
    0.32
    åIJįå½ķ
    0.32
    æľīåĵªäºĽ
    0.31
     Listed
    0.31
    åIJĦèĩªçļĦ
    0.31
    Activations Density 0.235%

    No Known Activations