© 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. 14628
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    contre
    -0.21
    seed
    -0.20
    êµ´
    -0.19
    sworth
    -0.19
    ago
    -0.19
    wright
    -0.19
    unj
    -0.18
    oker
    -0.18
    GS
    -0.17
    æ¥ł
    -0.17
    POSITIVE LOGITS
     маÑģÑĤеÑĢ
    0.20
    ä¸ĢåĽ¢
    0.19
    ativity
    0.19
     Æ¡n
    0.18
     BYU
    0.18
    iona
    0.18
    utz
    0.17
    UTE
    0.17
    åµ´
    0.17
    ORY
    0.17
    Activations Density 0.000%

    No Known Activations