© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 3145
    Prev
    Next
    INDEX
    Explanations

    color spectrum wavelengths

    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
    Negative Logits
    ä¾ĭè¡Į
    -0.28
    åIJİç»Ń
    -0.28
     setup
    -0.27
     overnight
    -0.27
     ÑģбоÑĢ
    -0.27
    åIJİåı°
    -0.26
     policy
    -0.26
     Overnight
    -0.25
    çĺ¸
    -0.25
    neau
    -0.24
    POSITIVE LOGITS
     sensations
    0.41
     percept
    0.40
     hues
    0.39
     colors
    0.35
     vibrations
    0.34
     ranges
    0.33
    èī²
    0.33
    æĦŁçŁ¥
    0.33
    对人ä½ĵ
    0.33
     extremes
    0.33
    Activations Density 0.035%

    No Known Activations