© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 13106
    Prev
    Next
    INDEX
    Explanations

    Panama and canal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    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
    fully
    -0.24
    ful
    -0.23
    ghi
    -0.19
    otten
    -0.19
    ç¼Ĺ
    -0.19
    ening
    -0.18
    FUL
    -0.18
    etical
    -0.17
    沫
    -0.17
    çĥ¬
    -0.17
    POSITIVE LOGITS
     Airways
    0.18
    LOGGER
    0.18
     atl
    0.17
     Panama
    0.17
    æ¹¾
    0.16
    åĽ½éĻħæľºåľº
    0.16
    ç®Ĺæĺ¯
    0.16
    æµ·åħ³
    0.16
    rist
    0.16
    åĶ¾
    0.16
    Activations Density 0.006%

    No Known Activations