© 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. 12680
    Prev
    Next
    INDEX
    Explanations

    days of the week

    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
    åī§ä¸Ń
    -0.20
    åŃļ
    -0.19
    ç¡®
    -0.19
    ç½ij讯
    -0.19
     Hurt
    -0.18
    åıĤåĬłä¼ļè®®
    -0.18
    ç½²
    -0.18
    åĨ³
    -0.18
    åĩºå¸Ńä¼ļè®®
    -0.18
    大çģ«
    -0.18
    POSITIVE LOGITS
    ä¾ĭè¡Į
    0.22
    åıĪæĺ¯
    0.21
    æ±½
    0.19
    _peak
    0.19
     thói
    0.18
     Sanford
    0.18
    หาย
    0.18
    aries
    0.18
    ®
    0.17
    âĦ¢
    0.17
    Activations Density 0.017%

    No Known Activations