© 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. 1743
    Prev
    Next
    INDEX
    Explanations

    center of places

    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
    Helmet
    -0.25
    äºĭ项
    -0.23
     partial
    -0.23
    奶ç²ī
    -0.23
    partial
    -0.23
    æĭŃ
    -0.22
    rtl
    -0.22
    stants
    -0.22
    RAY
    -0.21
    Partial
    -0.21
    POSITIVE LOGITS
    æ·±å¤Ħ
    0.31
    åľ°å¸¦
    0.29
    åľ°åĮºçļĦ
    0.28
    -west
    0.28
     Africa
    0.28
    most
    0.27
    è¡ĹåĮº
    0.27
     African
    0.26
    åŁİå¸ĤçļĦ
    0.26
    èħ¹
    0.25
    Activations Density 0.014%

    No Known Activations