© 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. 13212
    Prev
    Next
    INDEX
    Explanations

    internal revenue service

    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
    arity
    -0.20
    endTime
    -0.19
    nin
    -0.18
    ãģ¦ãĤĤ
    -0.17
    raises
    -0.17
    embr
    -0.16
    egg
    -0.15
    дÑĢ
    -0.15
    çĭĤ欢
    -0.15
    endDate
    -0.15
    POSITIVE LOGITS
     Cres
    0.17
    -approved
    0.17
    é«ĺæķĪ
    0.17
    åįļçī©
    0.17
    å±Ģ
    0.17
    夷
    0.16
    -backed
    0.16
    æ±ŁåĮĹ
    0.16
    Å¡t
    0.16
    laus
    0.15
    Activations Density 0.004%

    No Known Activations