© 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. 354
    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
    ä¸İåIJ¦
    -0.26
     Vera
    -0.22
     later
    -0.22
    åIJİéĿ¢çļĦ
    -0.22
     closer
    -0.22
    Availability
    -0.22
     sprint
    -0.22
    ÑĢез
    -0.22
     nearer
    -0.21
    ha
    -0.21
    POSITIVE LOGITS
     wedge
    0.26
    breaker
    0.25
    å¾Īå°ı
    0.23
    管çIJĨå±Ģ
    0.23
    iated
    0.23
    èŃ·
    0.22
     Rw
    0.22
    éļľç¢į
    0.22
    以éĺ²
    0.22
    owie
    0.21
    Activations Density 0.000%

    No Known Activations