© 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. 15058
    Prev
    Next
    INDEX
    Explanations

    taking office or assumed a position

    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
     Wan
    -0.21
    å¼Ń
    -0.19
    eur
    -0.19
     поÑĤом
    -0.18
    åħħ
    -0.18
    ocs
    -0.18
    åħħåĪĨä½ĵçİ°
    -0.18
     pans
    -0.18
    éļĶçĿĢ
    -0.18
    åĩºåı£
    -0.17
    POSITIVE LOGITS
    ä¸Ĭå²Ĺ
    0.26
    æİ¥æīĭ
    0.23
    roker
    0.22
    åıĸ代
    0.22
    è¿ĽæĿ¥
    0.20
    struments
    0.20
    ä¼Ĭå§ĭ
    0.20
    åħ¥èģĮ
    0.19
    etch
    0.19
    ici
    0.19
    Activations Density 0.079%

    No Known Activations