© 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. 1050
    Prev
    Next
    INDEX
    Explanations

    physics engine

    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
     census
    -0.25
    ĸī
    -0.24
     RequestContext
    -0.23
    æĻ®æŁ¥
    -0.23
     Verd
    -0.23
    dress
    -0.22
     discriminator
    -0.22
    CurrentValue
    -0.22
    ByPrimaryKey
    -0.22
    -directory
    -0.21
    POSITIVE LOGITS
    åĬĽåѦ
    0.38
    .gravity
    0.33
     physics
    0.33
     pallet
    0.31
     mechanics
    0.31
     gravity
    0.31
    秤
    0.31
     bouncing
    0.30
     Gravity
    0.29
    gravity
    0.29
    Activations Density 0.025%

    No Known Activations