© 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. 15540
    Prev
    Next
    INDEX
    Explanations

    agenda, days, reason, issue, options, phases

    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
    æ½Ń
    -0.19
    VertexBuffer
    -0.19
    åĵģä½į
    -0.18
    .loadData
    -0.18
    alu
    -0.18
    éĵĭ
    -0.18
    .getParam
    -0.17
    碲
    -0.17
    .getChildren
    -0.17
    ç¾½
    -0.17
    POSITIVE LOGITS
    åĪĻæĺ¯
    0.20
     singleton
    0.18
    浩
    0.18
    åĪĻ
    0.17
    äºĨä»ĸçļĦ
    0.17
     Executors
    0.17
     Swim
    0.17
    åĴĮæĶ¯æĮģ
    0.17
     Cavs
    0.17
    æ¶IJ
    0.17
    Activations Density 0.401%

    No Known Activations