© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 2733
    Prev
    Next
    INDEX
    Explanations

    prepositions and spatial relations

    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
    .opts
    -0.23
    goals
    -0.23
    èµĦæºIJåħ±äº«
    -0.23
    å¾Īéĩįè¦ģ
    -0.22
    æĮ¹
    -0.21
     metab
    -0.21
    ä¹Łå¥½
    -0.20
    кÑĤ
    -0.20
    ása
    -0.20
     IRepository
    -0.20
    POSITIVE LOGITS
    ukes
    0.23
     thereof
    0.22
    amb
    0.21
     Joined
    0.21
    roy
    0.21
    round
    0.21
    ait
    0.21
    Į¨
    0.21
     vicinity
    0.21
    輪
    0.20
    Activations Density 0.186%

    No Known Activations