© 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. 11163
    Prev
    Next
    INDEX
    Explanations

    can offer help

    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
    quarters
    -0.23
    mans
    -0.21
     gotta
    -0.19
    åĥ¦
    -0.19
    pill
    -0.19
    æł·çļĦ
    -0.19
    æĿ²
    -0.18
     genie
    -0.18
    zelf
    -0.17
    被人
    -0.17
    POSITIVE LOGITS
    å¸®ä½ł
    0.34
    为æĤ¨æıIJä¾Ľ
    0.31
    æıIJä¾Ľ
    0.27
    å¸¦ä½ł
    0.27
    ç»Ļä½ł
    0.25
    åijĬè¯īä½ł
    0.25
    让æĤ¨
    0.25
    åįıåĬ©
    0.24
    æıIJä¾ĽçļĦ
    0.24
    帮
    0.23
    Activations Density 0.029%

    No Known Activations