© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 3218
    Prev
    Next
    INDEX
    Explanations

    refereeing manager

    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
    Negative Logits
     isConnected
    -0.24
    çĪĨ款
    -0.24
    æĶ»æīĵ
    -0.23
     discoveries
    -0.23
    illard
    -0.22
    ¡°
    -0.22
     creative
    -0.22
    å¼ĢåºĹ
    -0.22
     creatively
    -0.22
    建åĨĽ
    -0.22
    POSITIVE LOGITS
    æī§æ³ķ
    0.40
    è£ģåĪ¤
    0.39
    çĽijçĿ£
    0.37
    è§ĦåĪĻ
    0.37
    仲è£ģ
    0.35
     referee
    0.35
    çĽij
    0.34
    è§ĦèĮĥ
    0.33
    åħ¬æŃ£
    0.33
    è¯Ħ审
    0.33
    Activations Density 0.034%

    No Known Activations