© 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. 16069
    Prev
    Next
    INDEX
    Explanations

    names, dates, and specific items

    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
    èĦĨ
    -0.21
    ç½IJ
    -0.21
    ouv
    -0.20
    иж
    -0.20
    ä¸Ģç¬Ķ
    -0.19
    éŀĭåŃIJ
    -0.19
    æŶè£ħ
    -0.18
    åıijåŀĭ
    -0.18
    auce
    -0.18
    ç¿ģ
    -0.18
    POSITIVE LOGITS
    åºĬ
    0.26
    åĪ¶åº¦æĶ¹éĿ©
    0.22
     beds
    0.20
    建设
    0.19
    -Version
    0.19
    æĺ¯æľĢ
    0.18
    å¸ĥç½®
    0.18
    åºĬä¸Ĭ
    0.18
    AdapterManager
    0.18
    åį§å®¤
    0.18
    Activations Density 0.003%

    No Known Activations