© 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. 16229
    Prev
    Next
    INDEX
    Explanations

    whether or implied

    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
    åħīèį£
    -0.22
    å¾Īæĸ¹ä¾¿
    -0.21
     Revolution
    -0.19
    åĪĨ辨
    -0.19
    lob
    -0.19
    å¾Ī满æĦı
    -0.19
    lobs
    -0.18
     entr
    -0.18
    _regular
    -0.18
     наблÑİ
    -0.18
    POSITIVE LOGITS
    究
    0.19
    ä¸į论
    0.19
     Ebay
    0.19
    łéĻ¤
    0.19
    责任
    0.18
     casualty
    0.18
    éļľ
    0.18
    ноÑģÑĤÑĮÑİ
    0.18
    丧失
    0.18
    çĽ²
    0.18
    Activations Density 0.138%

    No Known Activations