© 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. 15198
    Prev
    Next
    INDEX
    Explanations

    Sauvignon Blanc, Taj Mahal, medullaris, red wines

    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
    åİŁæĿ¥çļĦ
    -0.21
    åİŁæĿ¥
    -0.21
     requis
    -0.18
     Dex
    -0.18
    elib
    -0.18
    ervas
    -0.18
    è¨Ģ论
    -0.18
    erne
    -0.17
    oscope
    -0.17
    åī§
    -0.17
    POSITIVE LOGITS
    енн
    0.20
     fav
    0.19
    ä¿IJ
    0.19
    è¿ĺåİŁ
    0.18
    raud
    0.18
    羧
    0.18
    âĹĢ
    0.18
    åĩĢåĪ©æ¶¦
    0.18
    avid
    0.18
    ussion
    0.17
    Activations Density 0.002%

    No Known Activations