© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 1674
    Prev
    Next
    INDEX
    Explanations

    beyond expectations

    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
    åIJĪæ³ķæĢ§
    -0.24
     truth
    -0.23
     exh
    -0.23
     unge
    -0.22
    ä¸ĢåĪĻ
    -0.22
     tá»Ļi
    -0.21
     viability
    -0.21
     GiriÅŁ
    -0.21
    /math
    -0.21
    æĪĸèĢħåħ¶ä»ĸ
    -0.21
    POSITIVE LOGITS
    è¶ħåĩº
    0.32
    è¶ħè¶Ĭ
    0.31
     beyond
    0.30
     surpass
    0.29
     surpassed
    0.28
    ä¼ĺäºİ
    0.27
    è¾¾æłĩ
    0.27
    èĥ½è¾¾åĪ°
    0.24
    .super
    0.24
     exceeding
    0.24
    Activations Density 0.025%

    No Known Activations