© 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. 518
    Prev
    Next
    INDEX
    Explanations

    parent directory path

    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
     rg
    -0.26
    ç»´å°Ķ
    -0.24
    èĩªè§ī
    -0.23
    ONO
    -0.23
    atra
    -0.23
     whistle
    -0.22
    çĮ¿
    -0.22
    [".
    -0.22
     additional
    -0.21
    æ¿Ģ
    -0.21
    POSITIVE LOGITS
    Parent
    0.27
    parent
    0.25
    ä¸ĢæŃ¥
    0.23
    .Parent
    0.23
    breadcrumbs
    0.23
    ervisor
    0.23
    mega
    0.23
     atrás
    0.23
    kea
    0.23
    arent
    0.22
    Activations Density 0.034%

    No Known Activations