© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 229
    Prev
    Next
    INDEX
    Explanations

    drinking water

    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
    åİļåİļçļĦ
    -0.25
    ething
    -0.24
    èħĭ
    -0.23
    å¾Ĺ天
    -0.23
     added
    -0.22
     sacr
    -0.22
    è¿Ļç§įæĸ¹æ³ķ
    -0.22
    ими
    -0.22
     tán
    -0.21
     chaining
    -0.21
    POSITIVE LOGITS
    ä¿Ŀéļľ
    0.32
    å®īåħ¨
    0.29
    æģ¯æģ¯
    0.24
    å¸ĤæĶ¿
    0.24
    诰
    0.24
    åĽ½å®¶å®īåħ¨
    0.23
     nutshell
    0.23
    /live
    0.23
    å¥ij
    0.23
    Shield
    0.22
    Activations Density 0.011%

    No Known Activations