© 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. 11551
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation

    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
    æĢ§å¼º
    -0.19
     Bend
    -0.19
    èŁł
    -0.18
    ced
    -0.18
    å··
    -0.18
    itions
    -0.18
    èĬ±éĴ±
    -0.18
     lick
    -0.18
    NST
    -0.17
    使åħ¶
    -0.17
    POSITIVE LOGITS
    .Offset
    0.20
    à¹Ĥ
    0.20
    WindowSize
    0.20
    èIJ¥ä¸ļé¢Ŀ
    0.20
    èĬĥ
    0.19
     Trot
    0.18
    alu
    0.18
    çĶŁäº§è½¦éĹ´
    0.18
    rms
    0.17
    èĩªçĦ¶çķĮ
    0.17
    Activations Density 0.008%

    No Known Activations