© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 10334
    Prev
    Next
    INDEX
    Explanations

    exploit and prevent spam

    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
    Negative Logits
    éĴĹ
    -0.22
    溺
    -0.21
    ä¸İä¼Ĺ
    -0.20
    éľ¹
    -0.20
    ä¸ĬäºĨ
    -0.20
    èı°
    -0.19
    æ·±åİļçļĦ
    -0.18
    æĭĵå±ķ
    -0.18
    åħ¥èĤ¡
    -0.18
    éĢĤæŶ
    -0.18
    POSITIVE LOGITS
    è½»æĺĵ
    0.23
     looph
    0.23
    èĤ¼
    0.22
    ajar
    0.22
     exploits
    0.21
    æķıæĦŁ
    0.21
    å¼±çĤ¹
    0.21
    odem
    0.21
     exploit
    0.20
    æĶ»åĩ»
    0.20
    Activations Density 0.136%

    No Known Activations