© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12359
    Prev
    Next
    INDEX
    Explanations

    political parties

    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
    há»ķ
    -0.21
    æİ¢
    -0.20
    gow
    -0.20
     NSK
    -0.20
    æķ£
    -0.20
    å¢ŀåĬłåĢ¼
    -0.20
    _geom
    -0.19
    åľ°ä¸Ń
    -0.19
    kaar
    -0.19
    åIJĦè¡ĮåIJĦ
    -0.19
    POSITIVE LOGITS
     options
    0.22
    trad
    0.21
     branches
    0.21
    izz
    0.20
     arsen
    0.20
     Gro
    0.20
    ailing
    0.20
    Arch
    0.20
    oid
    0.20
    ä¹ħ
    0.20
    Activations Density 0.030%

    No Known Activations