© 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. 16159
    Prev
    Next
    INDEX
    Explanations

    political titles and roles

    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
    ä¸Ģä½ĵ
    -0.23
    èµĿ
    -0.23
    è¿Ļ对
    -0.20
    æ¼±
    -0.19
    æŃ£åľ¨è¿Ľè¡Į
    -0.19
    åIJį家
    -0.19
     ÑģÑĤоÑĢ
    -0.19
    沤
    -0.18
    ijo
    -0.18
    arra
    -0.18
    POSITIVE LOGITS
    å·
    0.22
    vez
    0.20
     Vine
    0.20
     prior
    0.20
    å¹²ä»Ģä¹Ī
    0.19
    çľĭä¸įåĩº
    0.18
    otech
    0.18
    æį
    0.18
    å¾ģæĶ¶
    0.18
    EV
    0.18
    Activations Density 0.018%

    No Known Activations