© 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. 13156
    Prev
    Next
    INDEX
    Explanations

    Westminster Abbey or Winchester

    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
    emi
    -0.19
    çĻ£
    -0.18
    -0.18
    ged
    -0.18
    umi
    -0.17
    æ·¤
    -0.17
    Credits
    -0.16
    speaker
    -0.16
    çĺĢ
    -0.16
    spot
    -0.16
    POSITIVE LOGITS
    пÑĢÑı
    0.18
    riors
    0.17
    lemn
    0.17
    ç¾±
    0.17
    é¢Ļ
    0.17
    bred
    0.17
    обÑĢаз
    0.17
    utzer
    0.17
    ature
    0.17
    yor
    0.16
    Activations Density 0.003%

    No Known Activations