© 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. 16225
    Prev
    Next
    INDEX
    Explanations

    killing and dying

    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
    çļĦæĸ¹å¼ıæĿ¥
    -0.19
     antid
    -0.19
    æľīæĽ´å¥½çļĦ
    -0.18
     dor
    -0.18
    aine
    -0.18
    çĶ¨èĩªå·±çļĦ
    -0.18
    æĿ¥æºIJäºİ
    -0.18
    .rx
    -0.17
     met
    -0.17
    ince
    -0.17
    POSITIVE LOGITS
    ä¸įå°ij
    0.26
    èĭ¥å¹²
    0.22
    äºĨä¸įå°ij
    0.20
    å®ĵ
    0.20
    æ°ijå±ħ
    0.20
    ä¹Łè®©
    0.19
    çķĻä¸ĭ
    0.19
    Affected
    0.19
    ä¸Ģ个å°ı
    0.19
    dam
    0.19
    Activations Density 0.063%

    No Known Activations