© 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. 261
    Prev
    Next
    INDEX
    Explanations

    device power and screen controls

    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
    çļĦåij½è¿IJ
    -0.26
    åij½è¿IJ
    -0.24
    ç¨Ģ
    -0.24
    éĵĭ
    -0.24
    orton
    -0.24
    æŀĦçŃij
    -0.23
    主è¦ģä»İäºĭ
    -0.23
    itori
    -0.23
    distributed
    -0.23
    ãĥĪãĥ³
    -0.23
    POSITIVE LOGITS
    æīĭåĬ¿
    0.37
     swipe
    0.36
     iOS
    0.33
     Xperia
    0.31
    Swipe
    0.31
     iphone
    0.30
    æīĭæľº
    0.30
    _ios
    0.30
     selfie
    0.30
     selfies
    0.29
    Activations Density 0.071%

    No Known Activations