© 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. 15457
    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
    invert
    -0.20
     Ze
    -0.20
     [...
    -0.18
     invert
    -0.18
     Nit
    -0.18
    å¥ī
    -0.17
    _NATIVE
    -0.17
    渡
    -0.17
     rack
    -0.17
     Jer
    -0.17
    POSITIVE LOGITS
    åħ¶å®ĥéĹ®é¢ĺ
    0.22
    åħ¨éķĩ
    0.21
    è¿Ļç§įæĸ¹æ³ķ
    0.20
    è¿Ļç§įæĸ¹å¼ı
    0.20
    æĭ¬
    0.20
    åħ³åģľ
    0.20
    çľī头
    0.19
    릿
    0.19
    å¦Ĥæŀľæ²¡æľī
    0.19
    éĨ´
    0.19
    Activations Density 0.000%

    No Known Activations