© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 817
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    _mv
    -0.26
     giriÅŁ
    -0.23
    æĬķåħ¥åĪ°
    -0.23
     rug
    -0.23
    æ·¦
    -0.23
    ouncy
    -0.22
    绩
    -0.22
     targetType
    -0.22
    \v
    -0.21
     Linear
    -0.21
    POSITIVE LOGITS
     territory
    0.25
    ardy
    0.24
    iscard
    0.23
    ä¸įå°ıçļĦ
    0.23
    ULK
    0.23
    ноÑģ
    0.23
    éĿ¢ç§¯çº¦
    0.23
    lore
    0.22
    嵯
    0.22
    /non
    0.22
    Activations Density 0.000%

    No Known Activations