© 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. 1071
    Prev
    Next
    INDEX
    Explanations

    organize, organization, management

    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
    ä¹ĭ乡
    -0.24
    æĬ¬
    -0.23
     Gow
    -0.23
    folk
    -0.23
    èĴĻ
    -0.22
     immersive
    -0.22
    -floor
    -0.22
    ipple
    -0.21
     twisted
    -0.21
     imm
    -0.21
    POSITIVE LOGITS
    æķ´çIJĨ
    0.44
    管çIJĨ
    0.40
    管çIJĨç³»ç»Ł
    0.39
    管çIJĨå·¥ä½ľ
    0.39
    管çIJĨä½ĵç³»
    0.37
    管çIJĨ模å¼ı
    0.36
    管çIJĨåĴĮ
    0.35
     management
    0.35
     orderly
    0.34
    家åĬ¡
    0.34
    Activations Density 0.049%

    No Known Activations