© 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. 668
    Prev
    Next
    INDEX
    Explanations

    naked

    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¯ı次
    -0.28
    åĬ¡å®ŀ
    -0.26
    åı£åij³
    -0.25
    èĩ´
    -0.24
    éĢĢä¼ij
    -0.24
    ä¿Ŀå®Ī
    -0.24
    æ¯ı次éĥ½
    -0.23
    å¤ļ次
    -0.23
    çĬ¬
    -0.23
    建ç«ĭ
    -0.23
    POSITIVE LOGITS
     naked
    0.41
     bare
    0.33
    裸
    0.32
     Bare
    0.32
     Naked
    0.31
    åıªåī©
    0.29
    åıªåī©ä¸ĭ
    0.29
     nude
    0.28
     nackt
    0.28
     nudity
    0.28
    Activations Density 0.011%

    No Known Activations