© 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. 11001
    Prev
    Next
    INDEX
    Explanations

    dates and locations

    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
     bureauc
    -0.20
     escal
    -0.20
    åľ°ä¸Ń
    -0.19
    åĨį说
    -0.18
    WithEmail
    -0.18
    å¼Ħ
    -0.17
     thieves
    -0.17
    èĵ¬
    -0.17
    EGIN
    -0.17
    æĪ¿éĹ´éĩĮ
    -0.17
    POSITIVE LOGITS
    ç»
    0.22
    :NO
    0.21
    .glob
    0.20
    'gc
    0.19
    URLConnection
    0.18
    imu
    0.18
    Coder
    0.17
    ĽĦ
    0.17
    roid
    0.17
    客æĪ·æľįåĬ¡
    0.17
    Activations Density 0.042%

    No Known Activations