© 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. 14367
    Prev
    Next
    INDEX
    Explanations

    controversy and heated debates

    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
     necessarily
    -0.19
    _boxes
    -0.19
    æ¼Ķä¹ł
    -0.19
     subscri
    -0.19
    _wp
    -0.19
    ÑıÑģÑĮ
    -0.18
     кÑĢоме
    -0.18
     Verfügung
    -0.18
    Throwable
    -0.17
    人çĶŁçļĦ
    -0.17
    POSITIVE LOGITS
    äºīè®®
    0.27
     controversy
    0.26
    è¯Ŀé¢ĺ
    0.25
    é¢ij
    0.24
    æĮĩè´£
    0.24
    æī¹è¯Ħ
    0.23
    çĦ¦çĤ¹
    0.23
     issues
    0.23
    é£İæ³¢
    0.23
    讳
    0.23
    Activations Density 0.165%

    No Known Activations