© 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. 16175
    Prev
    Next
    INDEX
    Explanations

    hostage crisis

    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
    æį§
    -0.21
    岿
    -0.21
    大家åĪĨ享
    -0.21
    èĩ´å¯Į
    -0.20
     perse
    -0.20
    åŃľ
    -0.20
    æ»ģ
    -0.19
     club
    -0.19
    æµģè¡Į
    -0.18
    æģ¨ä¸įå¾Ĺ
    -0.18
    POSITIVE LOGITS
     hostages
    0.27
    亲æĥħ
    0.24
     hostage
    0.24
     ETA
    0.23
     ransom
    0.23
    ç»ijæŀ¶
    0.22
     kidnapped
    0.21
    仵
    0.20
    security
    0.20
    ultimate
    0.20
    Activations Density 0.042%

    No Known Activations