© 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. 12496
    Prev
    Next
    INDEX
    Explanations

    of [place name]

    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
     decision
    -0.25
    è¿ĻäºĽ
    -0.22
    aks
    -0.22
    éĤ£äºĽ
    -0.21
     volum
    -0.21
    à¹Ĥรà¸ĩà¸ŀยา
    -0.21
    èĢĮä¸Ķ
    -0.21
     domain
    -0.20
    ä¸ĬéĿ¢
    -0.20
    å½¢
    -0.20
    POSITIVE LOGITS
     milfs
    0.25
    >NN
    0.25
    _:*
    0.23
    游æĪıåī¯æľ¬
    0.23
     fkk
    0.23
    å¸Ńæī§è¡Į
    0.22
     strapon
    0.21
    locator
    0.21
    ä¼ĺè¶Ĭ
    0.21
    综åIJĪå®ŀåĬĽ
    0.21
    Activations Density 0.006%

    No Known Activations