© 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. 14211
    Prev
    Next
    INDEX
    Explanations

    company names and suffixes

    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
    æŀľ
    -0.19
     ModelRenderer
    -0.19
    iska
    -0.19
     JsonRequest
    -0.19
    女çİĭ
    -0.19
    iap
    -0.18
    jug
    -0.18
    ä¾¦æŁ¥
    -0.17
    éªIJ
    -0.17
    inar
    -0.17
    POSITIVE LOGITS
     Corporation
    0.46
     corporation
    0.35
     CORPORATION
    0.34
     Corp
    0.33
    åħ¬åı¸çļĦ
    0.32
     Company
    0.31
    åħ¬åı¸
    0.31
    åħ¬åı¸å°Ĩ
    0.30
     company
    0.28
    æľīéĻIJåħ¬åı¸
    0.28
    Activations Density 0.074%

    No Known Activations