© 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. 968
    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
    ç»ĦåIJĪ
    -0.23
    çļĦä¸Ģ
    -0.23
    éĢłåŀĭ
    -0.23
    _ment
    -0.22
    Mp
    -0.22
     armour
    -0.22
    æľīä¸Ģ
    -0.22
    çļĦç¡®
    -0.21
     foil
    -0.21
     Armour
    -0.21
    POSITIVE LOGITS
     submissions
    0.24
     crossings
    0.23
    Annotations
    0.22
    åĪ°è´¦
    0.22
     Emerging
    0.22
     Corrections
    0.21
     nast
    0.21
     Nearby
    0.21
    ¢åįķ
    0.21
     Intersection
    0.21
    Activations Density 0.000%

    No Known Activations