© 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. 1647
    Prev
    Next
    INDEX
    Explanations

    bridge, tunnel, railway, canal

    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
     frat
    -0.27
     tether
    -0.26
    ç´IJ
    -0.25
    æľªç»ıæİĪæĿĥ
    -0.24
    æįĭ
    -0.23
    çĮĿ
    -0.23
     Washington
    -0.23
     клÑĥб
    -0.23
    archy
    -0.23
    Metro
    -0.23
    POSITIVE LOGITS
    åŀŃ
    0.27
    é«ĺå±±
    0.25
    æ°´åĪ©
    0.24
    å±±åĮº
    0.24
    fieldset
    0.24
    fte
    0.23
    çĿģå¼Ģ
    0.23
    éļ¾çĤ¹
    0.23
    akens
    0.23
     countryside
    0.23
    Activations Density 0.004%

    No Known Activations