© 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. 16076
    Prev
    Next
    INDEX
    Explanations

    vague, distant, or imprecise descriptions

    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
    å´Ľ
    -0.22
    毫ä¸įçĬ¹è±«
    -0.21
    Unhandled
    -0.21
    毫ä¸į
    -0.20
    ä¸į论æĺ¯
    -0.20
    缩çŁŃ
    -0.19
    sic
    -0.19
    ä¸Ŀ毫ä¸į
    -0.19
    ronic
    -0.19
    MetaData
    -0.19
    POSITIVE LOGITS
    ish
    0.25
    æĦıä¹īä¸Ĭ
    0.24
    æĦıä¹īä¸ĬçļĦ
    0.23
    ãģªãģĮãĤī
    0.23
     vaguely
    0.22
     notion
    0.22
    ly
    0.22
     notions
    0.21
    à¹Ĩ
    0.21
    许
    0.20
    Activations Density 0.023%

    No Known Activations