© 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. 1713
    Prev
    Next
    INDEX
    Explanations

    institutional clients and investors

    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
    è¾ħ导åijĺ
    -0.24
    Delimiter
    -0.23
     Mouth
    -0.23
    lessness
    -0.23
    è¨Ģè¯Ń
    -0.23
    _traits
    -0.23
    çģ«èĬ±
    -0.23
    åĴĮå®ĮåĸĦ
    -0.23
    æĻ®éĢļè¯Ŀ
    -0.23
    Verification
    -0.22
    POSITIVE LOGITS
    æĬķèµĦ
    0.31
    åºŀ大çļĦ
    0.30
     bulk
    0.29
    æľºæŀĦ
    0.28
    invest
    0.28
     investment
    0.28
    å·¨é¢Ŀ
    0.28
    ooled
    0.28
    åºŀ大
    0.27
     buys
    0.27
    Activations Density 0.027%

    No Known Activations