© 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. 15694
    Prev
    Next
    INDEX
    Explanations

    company acquisitions

    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
    æľį
    -0.20
    ä¸įåĪ©
    -0.19
    累累
    -0.18
    è®°
    -0.18
    UCT
    -0.18
    å¾Ģä¸ĭ
    -0.18
    说çļĦè¯Ŀ
    -0.18
    è¨ĺ
    -0.17
    éĿ¢åīį
    -0.17
    idal
    -0.17
    POSITIVE LOGITS
    æŃ¤ä¸¾
    0.24
     spokesman
    0.23
    æѤåīį
    0.22
    å°Ĩäºİ
    0.22
    åľ¨åħ¶
    0.22
    æŃ¤é¡¹
    0.21
     spokeswoman
    0.20
    (EXPR
    0.20
    åIJĮæŶè¿ĺ
    0.20
    .cy
    0.20
    Activations Density 0.187%

    No Known Activations