© 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. 11022
    Prev
    Next
    INDEX
    Explanations

    human cells, tissues, or tumors

    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
    人家
    -0.21
    åIJIJ槽
    -0.19
    abox
    -0.18
    躬
    -0.18
    çİ©ç¬ij
    -0.18
    ä¹IJ趣
    -0.18
     Danger
    -0.17
    èľ¥
    -0.17
    èı½
    -0.17
    åı¯æĢķçļĦ
    -0.17
    POSITIVE LOGITS
    -derived
    0.20
    çī¹æľīçļĦ
    0.20
    离
    0.20
    à¸ĺรรม
    0.20
    æ±īåŃIJ
    0.19
    -specific
    0.19
    åIJĮç±»
    0.19
    åĮĸè¿Ľç¨ĭ
    0.19
    å¹³æĿ¿
    0.19
    å¤ļå±Ĥ次
    0.19
    Activations Density 0.244%

    No Known Activations