© 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. 967
    Prev
    Next
    INDEX
    Explanations

    posters and merchandise

    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
    ADR
    -0.29
    èįIJ
    -0.23
    æĺİå¹´
    -0.23
    æĭ¨
    -0.22
     blasts
    -0.22
    .alert
    -0.21
    .Alert
    -0.21
    iones
    -0.21
    incr
    -0.21
    ibilit
    -0.20
    POSITIVE LOGITS
    è¡£
    0.27
    å¸Ĩ
    0.26
    åĽ¾æ¡Ī
    0.24
    çļĦè¡£æľį
    0.24
     order
    0.23
    秩åºı
    0.23
     mark
    0.22
    åºĹ主
    0.22
     ink
    0.21
     che
    0.21
    Activations Density 0.001%

    No Known Activations