© 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. 2794
    Prev
    Next
    INDEX
    Explanations

    astronomical and textual facts

    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
    ewise
    -0.27
     earthquake
    -0.25
    åĽ½æ°ijåħļ
    -0.24
    Battery
    -0.24
     elevation
    -0.24
     wheelchair
    -0.24
     Battery
    -0.23
     Delegate
    -0.23
    SPORT
    -0.23
     Yugoslavia
    -0.23
    POSITIVE LOGITS
     Neb
    0.31
    stellar
    0.30
     disk
    0.29
    .mas
    0.29
     neb
    0.29
    æĺŁéĻħ
    0.28
     cloud
    0.28
     dust
    0.28
    æ²ī积
    0.28
     deposits
    0.28
    Activations Density 0.066%

    No Known Activations