© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15151
    Prev
    Next
    INDEX
    Explanations

    loss of responsiveness signs

    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
    çļĦä¼ĺçĤ¹
    -0.20
    ä¸įéĶĻ
    -0.20
    ENO
    -0.19
     legend
    -0.19
     Ao
    -0.19
    .outputs
    -0.18
    çļĦä¼łç»Ł
    -0.18
    resident
    -0.18
    ä¹ĭç¾İ
    -0.18
    ãĤĤãģĤãĤĬ
    -0.18
    POSITIVE LOGITS
    æĪĸèĢħ
    0.37
    æĪĸ
    0.36
     or
    0.35
     æĪĸ
    0.32
    æĪĸå¤ļ
    0.32
     или
    0.32
    ê±°ëĤĺ
    0.31
     Ø£ÙĪ
    0.30
     hoặc
    0.30
    æĪĸèĢħæĺ¯
    0.29
    Activations Density 0.034%

    No Known Activations