© 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. 2875
    Prev
    Next
    INDEX
    Explanations

    co-chair, co-founder, co-host, co-director

    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
    å¾ĪæŃ£å¸¸
    -0.27
    æĦıä¹īä¸ĬçļĦ
    -0.23
    æĹłåħ³
    -0.22
    æĹłå¿§
    -0.22
    folk
    -0.21
    ĪæĿĥ
    -0.21
     coin
    -0.21
    æĻĤåĢĻ
    -0.20
    bone
    -0.20
    ERM
    -0.20
    POSITIVE LOGITS
    ãģ¥
    0.25
    åĪ¶
    0.24
     попÑĥ
    0.24
     Controllers
    0.23
    isms
    0.23
     annually
    0.23
     Controller
    0.22
    Controllers
    0.22
     offices
    0.22
    åħ¼
    0.22
    Activations Density 0.009%

    No Known Activations