© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15392
    Prev
    Next
    INDEX
    Explanations

    names and corporations

    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
    墨西
    -0.19
     bargain
    -0.18
    lags
    -0.17
     pier
    -0.17
    红æĹĹ
    -0.17
    oria
    -0.17
     challeng
    -0.17
    ä¸įå¼Ģ
    -0.17
    oned
    -0.17
     attitude
    -0.16
    POSITIVE LOGITS
    ASA
    0.20
    Loan
    0.18
    peek
    0.18
     peek
    0.18
    çĽijçĿ£ç®¡çIJĨ
    0.18
     Cyril
    0.18
    Alan
    0.17
    夫å¦ĩ
    0.17
    rema
    0.17
    ermen
    0.17
    Activations Density 0.353%

    No Known Activations