© 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. 13005
    Prev
    Next
    INDEX
    Explanations

    Q:

    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
    åįıä¼ļ
    -0.22
    两家
    -0.20
    uggy
    -0.19
    çļĤ
    -0.18
    KI
    -0.18
    æ··æ·Ĩ
    -0.18
    ully
    -0.18
    _operations
    -0.18
    atic
    -0.17
    讲究
    -0.17
    POSITIVE LOGITS
    tower
    0.20
    åĩłä¹İæīĢæľī
    0.19
    ellen
    0.18
    建çŃijä¸ļ
    0.17
    onte
    0.17
    åѦ龸
    0.17
    anut
    0.17
     Fathers
    0.17
    æĮ½
    0.17
    æ·Ģ
    0.16
    Activations Density 0.001%

    No Known Activations