© 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. 16892
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    OrCreate
    -0.22
    è¿ĻæĶ¯
    -0.20
    éĻĩ
    -0.20
    ernote
    -0.20
    æ´ij
    -0.19
    çIJĨä¼ļ
    -0.19
    ç¤ģ
    -0.19
    èĪĤ
    -0.19
    æŃ¤äºº
    -0.18
    åŃĶéĽĢ
    -0.18
    POSITIVE LOGITS
     ÑģобÑģÑĤвенно
    0.20
     заказ
    0.18
    å§Ķæīĺ
    0.18
    _DEAD
    0.18
    boo
    0.17
    itos
    0.17
     slug
    0.17
     stiff
    0.17
    çªģåĩºéĹ®é¢ĺ
    0.17
     <<=
    0.17
    Activations Density 0.000%

    No Known Activations