© 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. 12974
    Prev
    Next
    INDEX
    Explanations

    scale and size

    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
    Rick
    -0.22
    é¸Ń
    -0.21
    éªĤ
    -0.21
    æ³ķå®ļ代表
    -0.20
    夺
    -0.20
    _asc
    -0.19
    ç§ijæĬĢ大åѦ
    -0.19
    Pas
    -0.19
     Rick
    -0.18
    æľĢå¤ļ
    -0.18
    POSITIVE LOGITS
    è§Ħ模
    0.40
    è¦ı模
    0.33
    è§Ħ模åĮĸ
    0.31
     scale
    0.26
    æķĪçĽĬ
    0.24
    æľĢå°ı
    0.23
    ç»ĦåĽ¢
    0.23
    åѤåįķ
    0.22
     Scale
    0.21
    è¾ĥå°ı
    0.21
    Activations Density 0.171%

    No Known Activations