© 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. 15967
    Prev
    Next
    INDEX
    Explanations

    vein and circulation related conditions

    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
    æİ°
    -0.22
    大è¡Ĺ
    -0.21
    ahoma
    -0.20
    æijĩ头
    -0.20
    etch
    -0.20
    prepared
    -0.20
    çĤ¹çĩĥ
    -0.19
    è¿İåIJĪ
    -0.19
    åºļ
    -0.19
     TRADE
    -0.19
    POSITIVE LOGITS
    è¡Ģ液循çݯ
    0.25
    å¨ģå°¼æĸ¯äºº
    0.23
    åħĥå®Ŀ
    0.22
     Dup
    0.22
     giãn
    0.21
    å®ŀçī©
    0.21
    æµģéĩı
    0.21
     compression
    0.20
    诸èijĽ
    0.20
    åİĭ缩
    0.20
    Activations Density 0.084%

    No Known Activations