© 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. 14148
    Prev
    Next
    INDEX
    Explanations

    email forward headers

    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
    SKU
    -0.21
    ernes
    -0.21
    urtle
    -0.20
     onDataChange
    -0.20
    æ¯ıä¸Ģ
    -0.19
    éŨåīį
    -0.19
    "go
    -0.19
    ottes
    -0.19
     ethnic
    -0.19
    ultur
    -0.19
    POSITIVE LOGITS
    èģĮä¸ļæĬĢæľ¯
    0.25
     nghè
    0.23
    åĨ¼
    0.22
     NotÃŃc
    0.22
     ÐIJлекÑģан
    0.21
    ç¿»
    0.20
    åĨ°æ·ĩ
    0.20
    å¼ĢåıijèĢħ
    0.20
     reply
    0.20
    èĻº
    0.20
    Activations Density 0.082%

    No Known Activations