© 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. 17036
    Prev
    Next
    INDEX
    Explanations

    alleviating symptoms

    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
    gratis
    -0.21
    æĸ¯
    -0.19
     Alleg
    -0.19
    ãģŀ
    -0.19
    enton
    -0.19
    楷
    -0.18
    天空
    -0.18
     Slam
    -0.18
    éĢł
    -0.18
    åĽ½åº¦
    -0.18
    POSITIVE LOGITS
     symptoms
    0.28
    çĹĩçĬ¶
    0.28
    åĩıè½»
    0.20
    ç¼ĵ解
    0.20
    wm
    0.20
    æ°ĹæĮģãģ¡
    0.20
     Ñĥже
    0.20
    _existing
    0.20
    è¿ĻäºĽéĹ®é¢ĺ
    0.19
    æĹ¥ãĢħ
    0.19
    Activations Density 0.060%

    No Known Activations