© 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. 1915
    Prev
    Next
    INDEX
    Explanations

    technical or community topics

    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
    æĦŁ
    -0.24
    å¾Ģ
    -0.22
    </
    -0.22
    é¼»åŃIJ
    -0.21
    ..
    -0.21
    ãĥĦ
    -0.21
    æĬ¼
    -0.21
    isy
    -0.21
     sil
    -0.21
    yr
    -0.21
    POSITIVE LOGITS
    /grpc
    0.23
     Exists
    0.23
     capitals
    0.22
    SPATH
    0.21
    UTH
    0.21
    èı°
    0.21
     Joined
    0.20
    KHR
    0.20
    entral
    0.20
    /base
    0.19
    Activations Density 1.181%

    No Known Activations