© 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. 1457
    Prev
    Next
    INDEX
    Explanations

    highways and stations

    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
     Natur
    -0.24
    /entities
    -0.23
    toa
    -0.23
    .ttf
    -0.23
    Ordered
    -0.23
     themselves
    -0.22
    chez
    -0.22
    æľ¬åĽ½
    -0.22
     ourselves
    -0.21
    ä¸ŃåĽ½æĶ¿åºľ
    -0.21
    POSITIVE LOGITS
    交éĢļæŀ¢çº½
    0.29
    -access
    0.29
     highways
    0.28
    æĸ¹ä¾¿
    0.28
    ãĤ¢ãĤ¯ãĤ»ãĤ¹
    0.28
     accessible
    0.27
    å§Ĩ
    0.27
    便æį·
    0.26
     strategically
    0.26
     timely
    0.25
    Activations Density 0.034%

    No Known Activations