© 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
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 2885
    Prev
    Next
    INDEX
    Explanations

    ratings with stars

    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
    -facing
    -0.24
    æĪĸåħ¶ä»ĸ
    -0.23
    ikh
    -0.22
    prov
    -0.21
    .Suppress
    -0.21
     stud
    -0.21
    Confirmation
    -0.21
    æĢ§åĴĮ
    -0.21
     Shelter
    -0.21
     Stud
    -0.21
    POSITIVE LOGITS
     overall
    0.28
     neat
    0.27
    æĢ»ä½ĵ
    0.26
    overall
    0.25
    Overall
    0.24
     Overall
    0.24
    æķ´ä½ĵ
    0.23
    ilty
    0.23
    .operations
    0.23
    综åIJĪå®ŀåĬĽ
    0.23
    Activations Density 0.006%

    No Known Activations