© 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. 13012
    Prev
    Next
    INDEX
    Explanations

    anthropogenic changes and effects

    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
     miÄĻd
    -0.26
    <LM
    -0.23
    磨æįŁ
    -0.23
     erotisk
    -0.22
    stras
    -0.22
     uçu
    -0.21
    oldt
    -0.21
    innie
    -0.21
     Suspension
    -0.21
    èŀįåIJĪ
    -0.20
    POSITIVE LOGITS
    æĹ¥å¤ľ
    0.25
     caused
    0.23
     changes
    0.22
    åįŀ
    0.21
     caus
    0.21
    æķĪåºĶ
    0.21
    æ´ĭæ´ĭ
    0.21
    çŀĢ
    0.21
     causing
    0.20
    导èĩ´
    0.20
    Activations Density 0.011%

    No Known Activations