© 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. 303
    Prev
    Next
    INDEX
    Explanations

    order now

    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
    æĸ°éĹ»åıijå¸ĥ
    -0.26
    çļĦæĦŁè§ī
    -0.25
     democr
    -0.24
    çī©çIJĨåѦ
    -0.24
    çļĦè§ĤçĤ¹
    -0.24
    çļĦä¼Łå¤§
    -0.24
    çļĦ帮åĬ©
    -0.24
    æŀĦ件
    -0.24
    å¹´èĸª
    -0.23
    é»ĺé»ĺ
    -0.23
    POSITIVE LOGITS
    ä¸įå¾Ĺ
    0.31
    æľīæķĪæľŁ
    0.29
    å¼Ĥåľ°
    0.27
     validity
    0.27
     ineligible
    0.26
     resale
    0.26
     redemption
    0.26
    åºĹåĨħ
    0.25
     exclus
    0.25
     SINGLE
    0.25
    Activations Density 0.010%

    No Known Activations