© 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. 13400
    Prev
    Next
    INDEX
    Explanations

    account number

    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
    stral
    -0.19
    à¸ķะ
    -0.19
    éĬ®
    -0.19
    éľģ
    -0.18
    lob
    -0.17
     Walton
    -0.17
    KIT
    -0.17
    æĶ¹èī¯
    -0.17
    inic
    -0.17
    ãģ£ãģ
    -0.17
    POSITIVE LOGITS
    AndPassword
    0.20
    æĺ¯å¤ļå°ij
    0.19
    大åħ¨
    0.19
    å¤ļå°ij
    0.18
    æĮģæľī人
    0.18
    íĮIJ
    0.18
    åĴĮ
    0.18
    æĪĸ
    0.18
    isse
    0.17
     generators
    0.17
    Activations Density 0.034%

    No Known Activations