© 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. 16603
    Prev
    Next
    INDEX
    Explanations

    list conjunctions

    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
    æĪĸèĢħåħ¶ä»ĸ
    -0.22
    æĪĸåħ¶ä»ĸ
    -0.21
    åĮĸ
    -0.20
     conclus
    -0.18
     burg
    -0.18
    é«ĺéĢŁ
    -0.18
    imas
    -0.18
    SHOW
    -0.18
     Concurrent
    -0.18
     etc
    -0.17
    POSITIVE LOGITS
     alike
    0.20
    oose
    0.20
    agged
    0.20
    ively
    0.19
    mut
    0.19
    åĿĩå·²
    0.19
    umi
    0.18
    éĴĵ
    0.18
    åĿĩåı¯
    0.18
     lẫn
    0.18
    Activations Density 0.320%

    No Known Activations