© 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. 854
    Prev
    Next
    INDEX
    Explanations

    deficiency

    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
    é¢Ħå®ļ
    -0.27
     Count
    -0.25
    æıĴåħ¥
    -0.25
     Entrance
    -0.24
    å¸ĮæľĽèĥ½
    -0.24
     Composition
    -0.24
    ç¹ģ
    -0.24
    æĬĢæľ¯åĴĮ
    -0.23
    éĻĦåĬł
    -0.23
    è¿Ľåĩº
    -0.23
    POSITIVE LOGITS
     deficient
    0.39
     deficiencies
    0.37
     deficiency
    0.37
     caused
    0.33
    貧
    0.33
     inadequate
    0.31
    缺
    0.31
    åĮ®ä¹ı
    0.31
     symptoms
    0.30
    导èĩ´
    0.30
    Activations Density 0.217%

    No Known Activations