© 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. 14135
    Prev
    Next
    INDEX
    Explanations

    Google Maps and Earth Engine APIs

    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
    ãģ£ãģ±
    -0.20
    elage
    -0.19
    emies
    -0.19
    æ¾İæ¹ĥæĸ°éĹ»
    -0.19
    éĢīæĭ
    -0.19
    sWith
    -0.19
    amble
    -0.18
    itto
    -0.18
    社ä¼ļåĮĸ
    -0.18
     Rolling
    -0.18
    POSITIVE LOGITS
    href
    0.20
    åĩĨ
    0.19
    æµ·åºķ
    0.19
     schle
    0.18
    uez
    0.18
    zia
    0.18
     slur
    0.18
     vũ
    0.18
    ä¸Ĭç½ij
    0.18
    åºŀ大
    0.17
    Activations Density 0.008%

    No Known Activations