© 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. 11008
    Prev
    Next
    INDEX
    Explanations

    weather office predicts

    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
    使åħ¶
    -0.21
     ÙħÙĤابÙĦ
    -0.20
    SSERT
    -0.20
    HOLDER
    -0.19
    óa
    -0.18
     Cleaner
    -0.18
    inality
    -0.18
    -hook
    -0.18
    OTTOM
    -0.18
    constitutional
    -0.18
    POSITIVE LOGITS
    é¢ĦæĬ¥
    0.30
    é¢ĦèѦ
    0.28
    çģ¾å®³
    0.28
    åºĶæĢ¥ç®¡çIJĨ
    0.25
    çĽijæµĭ
    0.25
    èѦåijĬ
    0.25
    ä¸ĵ家
    0.25
    æĮĩ导ä¸ĭ
    0.25
    åºĶæĢ¥
    0.24
    温馨æıIJ示
    0.24
    Activations Density 0.015%

    No Known Activations