© 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. 14276
    Prev
    Next
    INDEX
    Explanations

    lemon tree, lemon drops, lemon cucumber

    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
    ingly
    -0.21
    åľ°ä¸Ńæµ·
    -0.17
    adin
    -0.16
    åıijå±ķæĸ¹åIJij
    -0.16
     Merry
    -0.15
    ä¸Ģè¶Ł
    -0.15
    immers
    -0.15
    way
    -0.15
     Narrow
    -0.15
    rics
    -0.14
    POSITIVE LOGITS
    ality
    0.20
    и
    0.17
     Dodd
    0.17
    beer
    0.16
    -taking
    0.16
    ¤í
    0.16
    iqu
    0.15
    åĴĮåıijå±ķ
    0.15
    æ±ł
    0.15
    ¼
    0.15
    Activations Density 0.013%

    No Known Activations