© 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
    2. Qwen3-8B
    3. 18-RESID-BATCHTOPK-65K__L0-80
    4. 2540
    Prev
    Next
    INDEX
    Explanations

    track and field events

    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
    æ¡§
    -0.28
    æµĵæµĵ
    -0.24
    ;++
    -0.23
    aviour
    -0.23
     intestine
    -0.22
     tourists
    -0.22
    岬
    -0.22
    橹
    -0.21
    æµ·åºķ
    -0.21
    红éħĴ
    -0.21
    POSITIVE LOGITS
    è·ijéģĵ
    0.33
    è¿IJåĬ¨ä¼ļ
    0.29
     athletics
    0.28
    è·ijæŃ¥
    0.28
    ä½ľçī©
    0.27
     Athletics
    0.27
    ç«¶
    0.25
     sprint
    0.25
    ItemType
    0.24
    åįķ项
    0.24
    Activations Density 0.007%

    No Known Activations