© 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
    2. Qwen3-8B
    3. 18-RESID-BATCHTOPK-65K__L0-80
    4. 90
    Prev
    Next
    INDEX
    Explanations

    volume or number indicator

    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
    Club
    -0.25
    PIN
    -0.24
     cool
    -0.22
    åħħç͵
    -0.22
    ceive
    -0.22
     erad
    -0.22
    _years
    -0.22
    æĹ¶ä»£çļĦ
    -0.21
    çĶľçĶľ
    -0.21
    ниÑĨ
    -0.21
    POSITIVE LOGITS
     containing
    0.27
    åĪ·
    0.26
    åĨĮ
    0.24
     Companion
    0.24
     facing
    0.24
    idas
    0.23
     Contents
    0.23
    çļĦä¸Ģéĥ¨åĪĨ
    0.23
    å¢ŀ
    0.23
    第åħŃ
    0.23
    Activations Density 0.048%

    No Known Activations