© 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. 12860
    Prev
    Next
    INDEX
    Explanations

    corporation names or organization titles

    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
    .Index
    -0.21
    æŁ©
    -0.19
    _index
    -0.19
    ä¸įå½±åĵį
    -0.19
    åİ¿åħ¬å®īå±Ģ
    -0.19
    éĿ¢å®¹
    -0.18
     combinations
    -0.18
    å¼Ģå¥ĸç»ĵæŀľ
    -0.18
    书éĻ¢
    -0.18
    èĥ½è¾¾åĪ°
    -0.18
    POSITIVE LOGITS
    åĨħéĥ¨
    0.23
    ä»»èģĮ
    0.22
     corporation
    0.21
    amp
    0.20
    é¦ĸå¸Ń
    0.20
    派驻
    0.20
    __,__
    0.20
     Corporation
    0.19
     Translate
    0.18
    å§Ķ
    0.18
    Activations Density 0.157%

    No Known Activations