© 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. 13100
    Prev
    Next
    INDEX
    Explanations

    politician,

    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
    оÑī
    -0.19
    çĥ¦æģ¼
    -0.18
    оÑĤоÑĢ
    -0.18
    人åĬĽ
    -0.18
     Geile
    -0.18
    -Semit
    -0.18
    åIJĦèĩªçļĦ
    -0.18
    课é¢ĺ
    -0.18
     Erotische
    -0.18
     rms
    -0.18
    POSITIVE LOGITS
    ä¹Ŀå¹´
    0.28
    åħ«å¹´
    0.28
    ä¸ĥå¹´
    0.25
    æĪIJ为ä¸ĢåIJį
    0.24
    åħŃå¹´
    0.23
    åįģå¹´
    0.23
    åĽĽå¹´
    0.23
    ä¸īå¹´
    0.21
    CCA
    0.21
    æݾ
    0.20
    Activations Density 0.171%

    No Known Activations