© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 2907
    Prev
    Next
    INDEX
    Explanations

    comfort and comfortability

    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
    æ³ķå®ļ
    -0.25
    è¡¨æł¼
    -0.24
    æĥħèĬĤ
    -0.23
    éģĹ迹
    -0.22
    åijĪ
    -0.22
    åľ¨åIJĮä¸Ģ
    -0.22
    æĦıä¹īä¸ĬçļĦ
    -0.22
    ém
    -0.22
    é»ijçĻ½
    -0.22
    缮å½ķ
    -0.21
    POSITIVE LOGITS
    èĪĴéĢĤçļĦ
    0.41
    èĪĴéĢĤ
    0.41
     comfortable
    0.35
     wearer
    0.33
    èĪĴæľį
    0.33
     confort
    0.32
     comfort
    0.32
    ä½ĵè´´
    0.31
    comfort
    0.30
     wear
    0.30
    Activations Density 0.013%

    No Known Activations