© 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. 12779
    Prev
    Next
    INDEX
    Explanations

    climate change and conditions

    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
    oci
    -0.18
    icular
    -0.17
    orial
    -0.17
    ä¾ĭè¡Į
    -0.17
    ness
    -0.17
    ળ
    -0.17
    limited
    -0.16
    @"
    -0.16
    []{"
    -0.16
    iveness
    -0.15
    POSITIVE LOGITS
    åıĺè¿ģ
    0.21
    çĤİçĥŃ
    0.19
    åŃ¦å®¶
    0.18
    åIJģ
    0.18
    -economic
    0.17
    åĭī
    0.17
    /community
    0.16
    /environment
    0.16
    æĿ¡ä»¶ä¸ĭ
    0.16
    meye
    0.16
    Activations Density 0.011%

    No Known Activations