© 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. 14648
    Prev
    Next
    INDEX
    Explanations

    asking or recommending action

    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
    asan
    -0.21
    æĺ¯æĪij
    -0.20
    åĨį说
    -0.20
    his
    -0.20
    æĺ¯æĪijçļĦ
    -0.19
    æĶ¹å»º
    -0.19
    GLOBALS
    -0.19
    hip
    -0.19
    åĪĽéĢłåĩº
    -0.18
    ãģ¡ãĤĩãģĨãģ©
    -0.18
    POSITIVE LOGITS
    ä¸įè¦ģ
    0.27
    éĺ²èĮĥ
    0.25
    åįĥä¸ĩä¸įè¦ģ
    0.24
    çķĻæĦı
    0.24
    å¸Ĥæ°ij
    0.23
    注æĦı
    0.23
    orra
    0.23
    å°½éĩı
    0.23
    广大å¸Ĥæ°ij
    0.22
    éģ¿åħį
    0.22
    Activations Density 0.028%

    No Known Activations