© 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. 14716
    Prev
    Next
    INDEX
    Explanations

    told X that Y

    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
    vid
    -0.20
    ä»Ĭ天å°ıç¼ĸ
    -0.20
    çľĭå¾ħ
    -0.19
    å°ıç¼ĸ
    -0.18
    åĪ°åºķ
    -0.18
    çľĭä¸Ģä¸ĭ
    -0.18
    elling
    -0.17
    ç»Ļä½ł
    -0.17
     cheapest
    -0.17
    abal
    -0.17
    POSITIVE LOGITS
    äºĨä¸Ģ份
    0.19
    åŃIJéĩĮ
    0.19
     Nunes
    0.19
    à¸ģะ
    0.19
    [of
    0.18
    Wrapped
    0.18
    主åĭķ
    0.18
    çĻ¸
    0.18
    çĻĥ
    0.18
    主åĬ¨
    0.18
    Activations Density 0.048%

    No Known Activations