© 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. 264
    Prev
    Next
    INDEX
    Explanations

    spelling bee, beauty pageant

    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
     commuting
    -0.24
    dw
    -0.22
     repaired
    -0.22
     docking
    -0.22
     holster
    -0.21
     inline
    -0.21
     Rust
    -0.21
    æ±ŁåĮĹ
    -0.21
    æĦŁåºĶ
    -0.21
    rust
    -0.21
    POSITIVE LOGITS
    /media
    0.29
    缼åħ¸
    0.27
    Formats
    0.26
    è§ĴéĢIJ
    0.26
    礼仪
    0.26
    -media
    0.26
    æ³³
    0.24
    èĢĥè¯Ħ
    0.24
    åħ¨çIJĥæľĢ大
    0.24
    -pol
    0.24
    Activations Density 0.005%

    No Known Activations