© 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. 15700
    Prev
    Next
    INDEX
    Explanations

    negative outcomes or consequences

    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
    ä¹ĭå¤ľ
    -0.24
    åīįä¸Ģ天
    -0.22
    åĩ»æĿĢ
    -0.22
    交éĢļå·¥åħ·
    -0.21
    åı¯è§Ĩ
    -0.21
    å°ıæŶåīį
    -0.21
    æݳ
    -0.20
    æĬĢæľ¯æĶ¯æĮģ
    -0.20
    åħ³éĶ®æĺ¯
    -0.20
    asma
    -0.20
    POSITIVE LOGITS
    åIJİæŀľ
    0.29
     consequences
    0.26
     consequence
    0.24
     later
    0.24
     eventually
    0.24
    åıįèĢĮ
    0.23
    æľĢç»Ī
    0.22
     ultimately
    0.22
     results
    0.22
    ately
    0.22
    Activations Density 0.125%

    No Known Activations