© 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. 11816
    Prev
    Next
    INDEX
    Explanations

    flooding damage and aftermath

    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
    éĽªèĬ±
    -0.27
    æŁĦ
    -0.23
    çĦ°
    -0.21
    åıijæī¬
    -0.20
    ç£ķ
    -0.20
    åĴ³åĹ½
    -0.20
    ç£ģåľº
    -0.19
    çĹĤ
    -0.19
    lfw
    -0.19
    çĥŁçģ«
    -0.19
    POSITIVE LOGITS
    ipes
    0.21
    å¤§éĽ¨
    0.21
    -hit
    0.20
    æ¶Ŀ
    0.20
     water
    0.20
    åĨľçĶ°
    0.20
    ewater
    0.20
    water
    0.20
    ä¸įåłª
    0.19
    æĿ¥è¢Ń
    0.19
    Activations Density 0.015%

    No Known Activations