© 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
    2. Qwen3-14B
    3. 20-RESID-BATCHTOPK-65K__L0-80
    4. 14227
    Prev
    Next
    INDEX
    Explanations

    critical fails, turned on, record-low

    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
    çļĦåĬ¨åĬĽ
    -0.21
    端
    -0.20
    iland
    -0.20
    æ°Ķè´¨
    -0.19
    å¾Ī容æĺĵ
    -0.19
    éĺµèIJ¥
    -0.18
     Rounded
    -0.18
    åºĶåıĬæĹ¶
    -0.18
     BEST
    -0.18
    erval
    -0.18
    POSITIVE LOGITS
    åIJ¦å®ļ
    0.32
    ä¸ĭéĻį
    0.27
    è´ŁéĿ¢
    0.26
     negative
    0.26
    åºŁ
    0.25
    è´¬
    0.24
     неÑĤ
    0.24
    ลà¸ļ
    0.24
    è²łãģij
    0.24
    涨åģľ
    0.23
    Activations Density 0.446%

    No Known Activations