© 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. 14394
    Prev
    Next
    INDEX
    Explanations

    allergy or restriction

    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
    omic
    -0.22
    é¼ĵèĪŀ
    -0.21
    æŃ£èĥ½éĩı
    -0.21
    襦
    -0.20
    çīĮçħ§
    -0.20
    çķ¹
    -0.20
    _seg
    -0.20
    epad
    -0.20
    èij¬
    -0.19
    å§ĺ
    -0.19
    POSITIVE LOGITS
    è¿ĩæķı
    0.26
    è±ģ
    0.23
     allergy
    0.23
     allerg
    0.22
    åĬ©
    0.21
    è¿ĩåħ³
    0.21
    ç¦ģ
    0.21
    ä¸įåIJ«
    0.20
    [label
    0.20
    -disabled
    0.20
    Activations Density 0.052%

    No Known Activations