© 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. 829
    Prev
    Next
    INDEX
    Explanations

    welcome and bonus items

    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
    Planet
    -0.27
    ä¸ĢçĶŁ
    -0.24
    auses
    -0.24
    åł¤
    -0.24
    åĨ¶çĤ¼
    -0.23
    createClass
    -0.23
    drv
    -0.23
     incompatible
    -0.22
    ή
    -0.22
    вали
    -0.22
    POSITIVE LOGITS
    å¤ĩçĶ¨
    0.37
     welcoming
    0.35
    æijĨæĶ¾
    0.34
     kindness
    0.32
     thoughtful
    0.31
    温馨æıIJ示
    0.31
    è´´å¿ĥ
    0.30
     bedside
    0.30
     welcome
    0.30
    æıIJä¾ĽçļĦ
    0.29
    Activations Density 0.014%

    No Known Activations