© 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. 16221
    Prev
    Next
    INDEX
    Explanations

    disability and ability

    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
    æĪŁ
    -0.20
    duplicate
    -0.19
    ä¾£
    -0.18
    æŃ¹
    -0.18
     uncert
    -0.18
    Ľ
    -0.18
    åĭŁéĽĨ
    -0.18
     ná»Ńa
    -0.17
    紧紧
    -0.17
    åıĺå¾ĹæĽ´åĬł
    -0.17
    POSITIVE LOGITS
     Sunshine
    0.20
     onKeyDown
    0.20
    fall
    0.19
    alker
    0.18
    yer
    0.18
     fall
    0.18
    æ´¼
    0.18
    éģĹå¿ĺ
    0.17
     means
    0.17
    hood
    0.17
    Activations Density 0.012%

    No Known Activations