© 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. 13123
    Prev
    Next
    INDEX
    Explanations

    state officials, police, or legislature

    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
    lat
    -0.19
    ä¸ĸçķĮä¸Ĭ
    -0.19
    ä½łè¦ģ
    -0.18
    apes
    -0.18
    paypal
    -0.18
    à¸ģารà¸Ĺำ
    -0.18
    pad
    -0.18
    .sky
    -0.17
    人çĶŁçļĦ
    -0.17
    (+
    -0.17
    POSITIVE LOGITS
    å±ĤéĿ¢
    0.24
    lessly
    0.22
    å·´å·´
    0.21
    индивид
    0.19
    交äºĴ
    0.18
    -level
    0.18
    æĺ¨
    0.18
    kür
    0.18
    äge
    0.18
    åıĬ以ä¸Ĭ
    0.18
    Activations Density 0.019%

    No Known Activations