© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 96
    Prev
    Next
    INDEX
    Explanations

    stock tickers and exchanges

    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
    å¹´ä¹ĭ
    -0.25
    ests
    -0.24
    Acknowled
    -0.24
    ç£ħ
    -0.23
    çļĦçĭ¬çī¹
    -0.23
    çĭ¬çī¹
    -0.22
    .proj
    -0.22
    æĶ¯éħį
    -0.22
    orsche
    -0.22
    tty
    -0.21
    POSITIVE LOGITS
    /download
    0.23
     conquest
    0.23
     Capitol
    0.22
    ä¸ĭè½½
    0.22
     download
    0.22
    纺
    0.21
     feather
    0.21
    âĹĢ
    0.21
     worst
    0.21
     Strateg
    0.21
    Activations Density 0.014%

    No Known Activations