© 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. 1430
    Prev
    Next
    INDEX
    Explanations

    electric vehicle and motors

    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
    èĿ®
    -0.24
    grammar
    -0.24
    macro
    -0.24
    æĸĽ
    -0.23
    æ··ä¹±
    -0.23
    ripe
    -0.23
     neckline
    -0.22
     Thanksgiving
    -0.22
    æĸIJ
    -0.21
    è¯Ńæ³ķ
    -0.21
    POSITIVE LOGITS
    çĶµåĬ¨è½¦
    0.35
     motors
    0.30
     battery
    0.30
     Battery
    0.29
    -powered
    0.29
    驱åĬ¨
    0.29
     Batter
    0.28
     batteries
    0.28
    纯çĶµåĬ¨
    0.28
     elect
    0.27
    Activations Density 0.020%

    No Known Activations