© 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. 11099
    Prev
    Next
    INDEX
    Explanations

    like or such as examples

    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
    ãĤ¤ãĥ¤
    -0.21
     ÑģоÑĤ
    -0.20
     оÑĩеÑĢед
    -0.19
    è¿Ļä¸Ģ
    -0.19
    SETS
    -0.19
    Selectors
    -0.18
    åľ¨çİ°åľº
    -0.18
    轨
    -0.18
    obe
    -0.18
     Incorporated
    -0.17
    POSITIVE LOGITS
    æ¯Ķå¦Ĥ
    0.30
    诸å¦Ĥ
    0.25
    èѬå¦Ĥ
    0.25
     namely
    0.24
    ä¾ĭãģĪãģ°
    0.24
    nam
    0.23
    ä¾ĭå¦Ĥ
    0.22
    æ¯Ķå¦Ĥ说
    0.22
    напÑĢимеÑĢ
    0.21
    eg
    0.18
    Activations Density 0.259%

    No Known Activations